In this episode, we talk all about connectomics - the study of animal brains - and how researchers at MIT have started leveraging AI to break through the primary bottleneck: brain image acquisition.

Podcast: Reverse Engineering The Brain With AI

Tandem solar cells based on perovskite semiconductors can convert sunlight into electricity more efficiently than conventional silicon solar cells.&nbsp;In order to bring this technology to market, stability and production processes must be further improved.&nbsp;Researchers from the Karlsruhe Institute of Technology (KIT) as well as the Helmholtz Imaging platforms at the German Cancer Research Center (DKFZ) and Helmholtz AI have now found a way to predict the quality of the perovskite layers and thus the solar cells: using machine learning and new artificial methods Intelligence (AI) allows this to be recognized during production from variations in light emission.&nbsp;The team reports on the results from which improved production processes can be derived in Advanced Materials (DOI: 10.1002/adma.202307160).Perovskite tandem solar cells combine a perovskite with a conventional solar cell, for example based on silicon.&nbsp;They are considered next-generation technology because, with an efficiency of currently more than 33 percent, they are much more efficient than conventional silicon solar cells - with inexpensive starting materials and simple manufacturing methods.&nbsp;The prerequisite for achieving this level of efficiency is a very high-quality and extremely thin perovskite layer, which is only a fraction of the thickness of a human hair.&nbsp;“One of the biggest challenges is to produce these high-quality so-called multicrystalline thin films using cost-effective and scalable processes without defects and holes,” explains tenure-track professor Ulrich W. Paetzold from the Institute of Microstructure Technology and the Light Engineering Institute of KIT.&nbsp;Even under apparently perfect conditions in the laboratory, unknown influences lead to fluctuations in the quality of the semiconductor layers: “This ultimately prevents the rapid start of industrial production of these highly efficient solar cells, which we so urgently need for the energy transition,” says Paetzold.<h2>AI finds hidden signs of a good coating</h2>In order to find out which factors influence the coating, an interdisciplinary team of perovskite solar cell experts from KIT teamed up with machine learning and explainable artificial intelligence (XAI) specialists from Helmholtz Imaging (at the DKFZ in Heidelberg) and Helmholtz AI ( at KIT).&nbsp;The researchers have developed AI methods that train and analyze so-called neural networks using a large data set.&nbsp;The data set includes video recordings of the photoluminescence of the perovskite thin films during the manufacturing process.&nbsp;Photoluminescence refers to the radiant emission of the semiconductor layers after excitation by an external light source.&nbsp;“Since even experts couldn’t see anything remarkable on the thin films, the idea arose to train an AI for machine learning (deep learning) to find hidden indicators of a good or bad coating in the millions of data from the videos,” explain Lukas Klein and Sebastian Ziegler from Helmholtz Imaging at the DKFZ. &nbsp; In order to filter and analyze the very broad information provided by deep learning AI, the researchers subsequently used methods of explainable artificial intelligence.<h2>“Blueprint for follow-up research”</h2>The result: In the experiment, the researchers were able to see that the photoluminescence varies during production and this influences the coating quality. “What was crucial in our work was that we specifically used XAI methods to see which factors would have to change for a high-quality solar cell,” said Klein and Ziegler. That is usually not the case. Most of the time, XAI is only used as a kind of guardrail to avoid errors when building AI models: “This is a paradigm shift, and the fact that we can systematically gain highly relevant findings in materials science in this way is new.” Because the answer is based on the variation of the Photoluminescence enabled the researchers to go further. After appropriate training of the neural networks, the AI was able to predict whether the solar cell would achieve low or high efficiency, depending on when and what variation in light emission occurred during production. “These are extremely exciting results,” says Ulrich W. Paetzold. “Thanks to the combined use of AI, we have an idea of which adjustments we need to make first in order to improve production. We can carry out our experiments in a more targeted manner and no longer have to search for a needle in a haystack in the dark. This is a blueprint for follow-up research, including for many other aspects in energy research and materials science.”<hr><h3>Original publication</h3>Lukas Klein, Sebastian Ziegler, Felix Laufer, Charlotte Debus, Markus Götz, Klaus Maier-Hein, Ulrich W. Paetzold, Fabian Isensee, Paul F. Jäger: Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI. Advanced Materials, 2023. DOI: 10.1002/adma.202307160

With the support of AI methods, researchers want to improve the manufacturing processes for highly efficient perovskite solar cells (Photo: Amadeus Bramsiepe, KIT)

Artificial intelligence methods show researchers the way to improved manufacturing processes for highly efficient solar cells - a blueprint for other research fields

AI for Perovskite Solar Cells: Key to Better Production

<h1 dir="ltr" id="isPasted">Introduction</h1>In an age where data is the new gold, and digital infrastructure forms the backbone of our society, the importance of data security cannot be overstated. Silicon-level security refers to the protective measures embedded at the hardware level of computing devices. It is a fundamental layer that underpins the reliability and trustworthiness of everything from consumer electronics to critical national infrastructure.As we usher in the era of ubiquitous computing, with billions of connected devices exchanging data every second, the stakes for robust security have never been higher. The concept of silicon-level security isn't new; however, the complexity and sophistication of threats it must mitigate have evolved dramatically. Gone are the days when simple perimeter defenses were sufficient. Today's security architects must assume a posture of 'defense in depth', where multiple layers of security measures are integrated into the silicon itself.This proactive approach to security is vital as the functionality and value of devices increasingly hinge on their ability to protect and process sensitive data securely. Whether it's financial transactions, personal information, or state secrets, the common denominator is the silicon that processes and stores this data. Thus, the integrity of silicon-level security mechanisms is a paramount concern, laying the foundation for trust in the digital age.In the following sections, we'll delve into the intricate world of secure interface technologies, unpack the challenges faced by modern System on Chip (SoC) designs, and explore how advancements in technology are paving the way for stronger, more resilient security measures. &nbsp;&nbsp;<h1 dir="ltr">The Backbone of Security: Root of Trust and Cryptography IP</h1>At the heart of silicon-level security is the concept of a 'Root of Trust' (RoT), a set of functions trusted implicitly by the system due to their foundational role in ensuring overall security. The RoT provides a secure starting point for system boot and cryptographic operations and is immune to software-based attacks because it is often implemented in hardware. This secure cornerstone handles critical tasks such as secure boot, secure firmware updates, and cryptographic key management, ensuring that only authenticated code and communications are running on the device.Adjacent to the Root of Trust is the role of Cryptography IP, which includes hardware-based cryptographic engines designed to perform encryption and decryption tasks. These cryptographic modules serve as the workhorses for data protection, enabling secure data storage and transmission, and are essential for functions like secure communications, digital signatures, and user authentication.Both RoT and Cryptography IP are imperative for a secure boot process, which is the first step in a secure chain of events that occur when a device is powered on. During this process, the integrity and authenticity of the software stack are verified using cryptographic checks, establishing a secure execution environment from the outset.To understand their importance, consider the analogy of a bank vault. In this analogy, RoT is the combination to the vault—highly confidential and used to validate the identity of individuals attempting to access the vault. Cryptography IP, on the other hand, is like the reinforced walls and time-locked doors—structural features that enforce security protocols and prevent unauthorized access.These technologies also enable secure end-to-end communication, ensuring that data remains confidential and unaltered during transmission. With the proliferation of the Internet of Things (IoT) and connected devices, securing data in transit has become as crucial as securing it at rest.Despite their robustness, the implementation of Root of Trust and Cryptography IP is not without challenges. Ensuring that these security measures themselves are impervious to exploitation requires meticulous design and regular updates in response to the evolving threat landscape. In the next section, we will examine the security challenges inherent in modern SoC designs and discuss how these foundational technologies can help mitigate those risks.<h1 dir="ltr">Securing the Core: Challenges in SoC Designs</h1>Modern Systems on Chip (SoCs) are marvels of integration, embedding processors, memory, I/O, and various other functionalities into a single chip. This consolidation brings vast benefits in terms of performance and power efficiency but also introduces a myriad of security challenges that must be navigated carefully.One of the primary challenges is the increased attack surface. The very features that make SoCs powerful—connectivity, configurability, and smart functionalities—also make them more vulnerable to attacks. With more lines of code, there are more potential bugs or backdoors. With more interfaces, there are more points of entry for malicious actors.Additionally, as SoCs become more complex, ensuring that every component is secure from design to decommission becomes harder. This complexity often results in a greater risk of side-channel attacks, where an attacker could infer sensitive information from power consumption, electromagnetic emissions, or even computation time.Supply chain security presents another significant challenge. SoCs are global products, with materials and components sourced from and passing through multiple vendors and countries. Each step in this chain presents an opportunity for malicious actors to introduce vulnerabilities.Moreover, the need for speed in markets means that security can sometimes be an afterthought, leading to vulnerabilities in the rush to get products to market. As a result, rigorous security testing and validation procedures are essential but can be overlooked or undervalued.In dealing with these challenges, the industry has turned to a variety of mitigation strategies. One key approach is the concept of 'security by design', where security measures are considered at every step of the SoC design and manufacturing process. This approach includes using hardware-based security features, like those provided by secure enclaves and trusted execution environments, which can isolate sensitive operations from the main processor to protect them from software attacks.Another strategy is regular security audits and updates. Even after an SoC is deployed, its security posture must be maintained and updated in response to new threats—much like how software is regularly patched.Finally, leveraging advanced fabrication techniques and materials can reduce the physical vulnerabilities of SoCs, making them harder to tamper with or reverse engineer.Navigating these challenges is a complex task, but it is one that is crucial for maintaining trust in technology. In the next section, we discuss how these strategies are put into practice, keeping SoCs secure against an ever-evolving array of threats.<h1 dir="ltr">Building Defenses: Mitigation Strategies for SoC Security</h1>To confront the security challenges in SoC designs, the semiconductor industry has developed a suite of mitigation strategies that bolster the defenses of these complex systems.<ul><li dir="ltr">Secure Architectural Design: The first line of defense is secure architectural design. This includes the incorporation of hardware-based security features such as secure boot, trusted execution environments, and secure key storage. By integrating these elements at the design phase, SoCs are better equipped to handle unauthorized access attempts and ensure that critical operations remain uncompromised.</li><li dir="ltr">Layered Security Approach: A layered security approach is critical for protecting against a wide range of potential attacks. This involves implementing multiple security layers that function together to protect the system. If one layer is breached, the subsequent layers provide an additional level of defense, making it more difficult for an attack to be successful.</li><li dir="ltr">Dynamic Security Measures:&nbsp;Dynamic security measures, such as runtime monitoring and anomaly detection, are also key. These systems can detect and respond to suspicious behavior in real-time, providing a responsive layer of security that adapts to current threats.</li><li dir="ltr">Encryption and Cryptography:&nbsp;Strong encryption and cryptography are indispensable in SoC security, safeguarding data both at rest and in transit. Advanced encryption standards and cryptographic algorithms are implemented to ensure that even if data is intercepted, it remains indecipherable without the appropriate keys.</li><li dir="ltr">Regular Security Audits and Firmware Updates:&nbsp;Ongoing security audits and regular firmware updates ensure that security measures remain up-to-date in the face of evolving threats. This strategy includes the establishment of secure update mechanisms that prevent the installation of malicious firmware.</li><li dir="ltr">Supply Chain Integrity:&nbsp;Protecting the integrity of the supply chain is another critical strategy. This involves measures such as secure manufacturing practices, tamper-evident packaging, and traceability of components to ensure that SoCs are not compromised at any point from fabrication to delivery.</li><li dir="ltr">User Education and Access Control: Lastly, user education and strict access control policies are necessary to prevent inadvertent breaches. Users need to be aware of the security features of their devices and how to use them properly, while access control ensures that only authorized individuals can make changes to the system configuration or access sensitive information.</li></ul>By implementing these strategies, SoC designers and manufacturers can create more secure systems that are resilient in the face of both current and emerging security threats. However, the fast pace of technological change means that vigilance and continuous improvement are mandatory. Security is not a one-time achievement but an ongoing process of adaptation and reinforcement.<h1 dir="ltr">Conclusion</h1>Silicon-level security stands as a critical pillar in our digital era. Through exploring secure interface technologies, such as Root of Trust and Cryptography IP, we recognize their indispensable role in safeguarding modern SoCs. As we confront security challenges—from side-channel attacks to complex interface vulnerabilities—the need for a robust, multi-layered defense strategy becomes clear.Securing silicon goes beyond a single solution—it's a continuous battle, balancing innovation with vigilance. As technology advances, so must our security strategies, integrating state-of-the-art features and adopting a culture of security-first in design and deployment.The future hinges on our collective effort to ensure the trustworthiness of our digital foundations. In fostering this trust, the commitment to silicon-level security must remain unwavering, uniting stakeholders across the industry to fortify our digital landscape.<h1 dir="ltr">Synopsys' Impact on SoC Security</h1>In the realm of SoC security, <a href="https://www.synopsys.com/" target="_blank" rel="noopener noreferrer">Synopsys</a> offers critical technologies that sharpen the defenses of silicon interfaces. Their AI and Machine Learning tools not only expedite chip design but also imbue systems with smart threat detection, essential for anticipatory security. Their cloud solutions provide secure integrations essential for IoT devices dependent on cloud data management.Their Design Technology Co-Optimization (DTCO) propels the creation of SoCs resistant to advanced threats by exploring new transistor architectures. Synopsys' emphasis on early-stage security integration through DevSecOps, alongside energy-efficient design practices, further strengthens SoCs against exploits like power analysis attacks.Synopsys also pioneers in fortifying system integrity with its Multi-Die System solutions, safeguarding sensitive operations within SoCs. Their vigilance extends to software security, ensuring open-source components and software supply chains are robust against vulnerabilities from inception.Through innovation and a strategic approach to security, Synopsys plays a pivotal role in the evolution of more secure digital infrastructures, demonstrating a comprehensive commitment to the advancement of SoC security.<h1 dir="ltr" id="isPasted">References</h1>[1] Dana Neustadter, Hezi Saar, Michael Posner, ‘How Security for SoC Interfaces Enhances Data Protection’, Synopsis, 4 Oct. 2022, [Online], Available from:&nbsp;<a href="https://www.synopsys.com/blogs/chip-design/soc-interfaces-security-enhance-data-protection.html" target="_blank">https://www.synopsys.com/blogs/chip-design/soc-interfaces-security-enhance-data-protection.html</a>[2] Marco Ciaffi, John Min, ‘Building security into an AI SoC using CPU features with extensions’, Embedded, 12 Apr. 2021, [Online], Available from:&nbsp;<a href="https://www.embedded.com/building-security-into-an-ai-soc-using-cpu-features-with-extensions/" target="_blank">https://www.embedded.com/building-security-into-an-ai-soc-using-cpu-features-with-extensions/</a>[3] Ruud Derwig, Nicole Fern, ‘Techniques for Ensuring Security in Processor-based SoCs’, Synopsis, [Online], Available from: <a href="https://www.synopsys.com/designware-ip/technical-bulletin/ensuring-security-processor-socs.html" target="_blank">https://www.synopsys.com/designware-ip/technical-bulletin/ensuring-security-processor-socs.html</a>[4] Landry J., ‘What Is Hardware Root of Trust?’, Dell, 22 July 2022, [Online], Available from: <a href="https://www.dell.com/en-us/blog/hardware-root-trust/" target="_blank" rel="noopener noreferrer">https://www.dell.com/en-us/blog/hardware-root-trust/</a>

Silicon-level security is crucial in protecting the hardware of computing devices, serving as a foundational layer for data integrity and system reliability in our increasingly digital world.


Silicon-Level Security: A Deep Dive into Secure Interfaces

This article was discussed in our <a href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/a04f438a-330e-4e3b-b5b5-d78d1bba7768?dark=false" class="fr-draggable" data-gtm-yt-inspected-9="true" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> The full article will continue below.<hr>With 3D inkjet printing systems, engineers can fabricate hybrid structures that have soft and rigid components, like robotic grippers that are strong enough to grasp heavy objects but soft enough to interact safely with humans.These multimaterial 3D printing systems utilize thousands of nozzles to deposit tiny droplets of resin, which are smoothed with a scraper or roller and cured with UV light. But the smoothing process could squish or smear resins that cure slowly, limiting the types of materials that can be used.&nbsp;Researchers from MIT, the MIT spinout Inkbit, and ETH Zurich have developed a new 3D inkjet printing system that works with a much wider range of materials. Their printer utilizes computer vision to automatically scan the 3D printing surface and adjust the amount of resin each nozzle deposits in real-time to ensure no areas have too much or too little material.Since it does not require mechanical parts to smooth the resin, this contactless system works with materials that cure more slowly than the acrylates which are traditionally used in 3D printing. Some slower-curing material chemistries can offer improved performance over acrylates, such as greater elasticity, durability, or longevity.In addition, the automatic system makes adjustments without stopping or slowing the printing process, making this production-grade printer about 660 times faster than a comparable 3D inkjet printing system.The researchers used this printer to create complex, robotic devices that combine soft and rigid materials. For example, they made a completely 3D-printed robotic gripper shaped like a human hand and controlled by a set of reinforced, yet flexible, tendons.<iframe width="640" height="360" src="https://www.youtube.com/embed/mw9hYHoD46o?&amp;wmode=opaque&amp;rel=0&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-gtm-yt-inspected-9="true" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&nbsp;&nbsp;&nbsp;</iframe>“Our key insight here was to develop a machine-vision system and completely active feedback loop. This is almost like endowing a printer with a set of eyes and a brain, where the eyes observe what is being printed, and then the brain of the machine directs it as to what should be printed next,” says co-corresponding author Wojciech Matusik, a professor of electrical engineering and computer science at MIT who leads the Computational Design and Fabrication Group within the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL).He is joined on the paper by lead author Thomas Buchner, a doctoral student at ETH Zurich, co-corresponding author Robert Katzschmann PhD ’18, assistant professor of robotics who leads the Soft Robotics Laboratory at ETH Zurich; as well as others at ETH Zurich and Inkbit. The research appears today in Nature.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzAwMTA1ODQ1NTg1LU1JVC1WaXNpb25KZXR0aW5nLTAyLXByZXNzLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 766px;" class="fr-fic fr-dib">The researchers used their printing system to create complex, robotic devices that combine soft and rigid materials. Since the printer has 16,000 nozzles, the system can control fine details of the device being fabricated. This rendering shows objects that have been halfway built by the printer. Credit: Courtesy of the researchers<h2>Contact free</h2>This paper builds off a low-cost, multimaterial 3D printer known as <a href="https://news.mit.edu/2015/multifab-3-d-print-10-materials-0824" target="_blank">MultiFab</a> that the researchers introduced in 2015. By utilizing thousands of nozzles to deposit tiny droplets of resin that are UV-cured, MultiFab enabled high-resolution 3D printing with up to 10 materials at once.With this new project, the researchers sought a contactless process that would expand the range of materials they could use to fabricate more complex devices.They developed a technique, known as vision-controlled jetting, which utilizes four high-frame-rate cameras and two lasers that rapidly and continuously scan the print surface. The cameras capture images as thousands of nozzles deposit tiny droplets of resin.The computer vision system converts the image into a high-resolution depth map, a computation that takes less than a second to perform. It compares the depth map to the CAD (computer-aided design) model of the part being fabricated, and adjusts the amount of resin being deposited to keep the object on target with the final structure.The automated system can make adjustments to any individual nozzle. Since the printer has 16,000 nozzles, the system can control fine details of the device being fabricated.“Geometrically, it can print almost anything you want made of multiple materials. There are almost no limitations in terms of what you can send to the printer, and what you get is truly functional and long-lasting,” says Katzschmann.The level of control afforded by the system enables it to print very precisely with wax, which is used as a support material to create cavities or intricate networks of channels inside an object. The wax is printed below the structure as the device is fabricated. After it is complete, the object is heated so the wax melts and drains out, leaving open channels throughout the object.Because it can automatically and rapidly adjust the amount of material being deposited by each of the nozzles in real time, the system doesn’t need to drag a mechanical part across the print surface to keep it level. This enables the printer to use materials that cure more gradually, and would be smeared by a scraper.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzAwMTA1ODc2NjQxLU1JVC1WaXNpb25KZXR0aW5nLTA1LXByZXNzLmpwZyIsImVkaXRzIjp7InJlc2l6ZSI6eyJ3aWR0aCI6OTUwLCJmaXQiOiJjb3ZlciJ9fX0=" style="width: 766px;" class="fr-fic fr-dib">A photograph shows a variety of 3D-printed objects in white, displayed on a tray. The objects are: a robotic hand, cubes made of lattice structures, a biological heart, and a walking robot. Credit: Courtesy of the researchers<h2>Superior materials</h2>The researchers used the system to print with thiol-based materials, which are slower-curing than the traditional acrylic materials used in 3D printing. However, thiol-based materials are more elastic and don’t break as easily as acrylates. They also tend to be more stable over a wider range of temperatures and don’t degrade as quickly when exposed to sunlight.“These are very important properties when you want to fabricate robots or systems that need to interact with a real-world environment,” says Katzschmann.The researchers used thiol-based materials and wax to fabricate several complex devices that would otherwise be nearly impossible to make with existing 3D printing systems. For one, they produced a functional, tendon-driven robotic hand that has 19 independently actuatable tendons, soft fingers with sensor pads, and rigid, load-bearing bones.“We also produced a six-legged walking robot that can sense objects and grasp them, which was possible due to the system’s ability to create airtight interfaces of soft and rigid materials, as well as complex channels inside the structure,” says Buchner.The team also showcased the technology through a heart-like pump with integrated ventricles and artificial heart valves, as well as metamaterials that can be programmed to have non-linear material properties.“This is just the start. There is an amazing number of new types of materials you can add to this technology. This allows us to bring in whole new material families that couldn’t be used in 3D printing before,” Matusik says.The researchers are now looking at using the system to print with hydrogels, which are used in tissue-engineering applications, as well as silicon materials, epoxies, and special types of durable polymers.They also want to explore new application areas, such as printing customizable medical devices, semiconductor polishing pads, and even more complex robots.

This rendering shows a robot being built layer-by-layer using the new process. The black spheres represent the material that the printer uses. The material is then cured by UV light, represented in blue. At the top of the image are the cameras that scan the procedure and adjust accordingly. Image: Moritz Hocher

Computer vision enables contact-free 3D printing, letting engineers print with high-performance materials they couldn’t use before.

This 3D printer can watch itself fabricate objects

This article was discussed in our <a href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/2dca102f-80d1-4182-8d29-b2f6cf6ed323?dark=false" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> The full article will continue below.<hr>Now that ChatGPT has revealed connections in meaning that can emerge from the simple premise of predicting the next word, a team of researchers led by the University of Michigan aims to do the same for atoms strung together to build molecules.The research is supported with a one-year grant from the Department of Energy providing 200,000 node hours on <a href="https://www.alcf.anl.gov/polaris" target="_blank" rel="noreferrer noopener">Polaris, a 34-petaflop supercomputer</a> at Argonne National Laboratory. The team will build a foundational model for molecules, similar to the GPT models that support applications like ChatGPT. The new model will focus on small organic molecules with relevance to energy storage and conversion applications—mainly composed of carbon, hydrogen, oxygen and nitrogen.“What we’ve learned from language models is that size matters. The interesting behavior happens when you make it very big,” said <a href="https://aero.engin.umich.edu/people/viswanathan-venkat/" target="_blank" rel="noreferrer noopener">Venkat Viswanathan</a>, U-M associate professor of aerospace engineering and principal investigator of the award. “If you train on a small amount of data and ask it to write Shakespeare, it’s not good. But a larger data set is better, and when it’s big enough, text that sounds like Shakespeare emerges.”The team is planning to use their model to predict better battery electrolytes—the medium through which ions shuttle from one electrode to the other during charge and discharge cycles. Many electrode pairs offer the potential for higher energy densities than our current lithium-based batteries, but the electrolyte needs to work with both electrodes. That’s often a tall order, and the team is betting AI can help.As with GPT’s steady diet of text with no annotation, the chemical model will be fed text-based representations of atomic structures with no additional information like chemical properties.“There are several billions of molecules that are possible to make, and we have the text-based representation for them,” Viswanathan said. “Our slice of that will be synthesizable small molecules similar to those used in pharmaceuticals and electrolytes.”When the model is able to predict missing atoms in small organic compounds, the team will move on to fine-tuning—feeding it the properties of some compounds and asking it to predict the properties of others. Through iterative feedback, they intend to build an AI that can master small organic molecule chemistry.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzAwMTA1MjE3NTA5LW1vZGVsLWRpYWdyYW0uanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib">The diagram shows 2D representations of molecular structures on the left, simplified to text representations in the arrows and then mapped by the foundational model in a way that enables it to predict molecular properties and design molecules with the right properties. Credit: Viswanathan Group, University of Michigan“Deep Forest Sciences has built considerable expertise in applying molecular foundation models to drug discovery, and we are excited to apply that knowledge to batteries,” said Bharath Ramsundar, founder and CEO of Deep Forest Sciences, and a key collaborator in building the model.&nbsp;Once the model is up and running, the team will ask it to predict electrolytes suited to a particular pair of electrodes. It will then experimentally test each prescription in the lab with a robotic setup, Clio, that was developed by Viswanathan and collaborator <a href="https://www.cmu.edu/epp/people/faculty/jay-f-whitacre.html" target="_blank" rel="noreferrer noopener">Jay Whitacre</a>, professor of materials science, engineering and public policy at Carnegie Mellon University.They are also looking for new design rules that may emerge from the model—rules that humans haven’t been able to consider.“When we learn chemistry, we learn each rule, and then we learn about a dozen exceptions,” Viswanathan said. “Can this now help us learn better rules or be able to design with more sophisticated combined rules?”As an example, he said that it was easy for humans to add one atom to a structure and see whether it works or not. Adding pairs of atoms to the structure at different locations results in too many possibilities for humans to easily parse. But AI might be able to do it.The DOE’s <a href="https://science.osti.gov/ascr/Facilities/Accessing-ASCR-Facilities/INCITE/About-incite" target="_blank" rel="noreferrer noopener">INCITE program</a>, which provides the funding for this study, was conceived to seek out computationally intensive, large-scale research projects with the potential to significantly advance key areas in science and engineering.

Taking inspiration from the word-predicting large language models, a U-M team is kickstarting an atom-predicting model with 200,000 node hours on Argonne’s Polaris.

Building a chemical 'GPT' to help design a key battery component

Maximizing human abilities, passing on skills and abilities to new generations, eliminating societal inequality – achieving these goals will require solving a variety of problems affecting existing educational and training methods and the development and deployment of new methods. Education and training are indispensable to the upbringing of a new generation to shoulder future responsibilities and to generating the driving force needed to change society and industry to make them both more vigorous and more sustainable.&nbsp;In response to this social need, efforts making use of the latest technologies to develop and implement new educational methods are becoming more active. Here we describe a movement known as “Edu Tech” that encourages the development of new technology to bring about major changes in educational methods (Figure 1).<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzAwMTA0NTY4OTEyLXZhcmlvdXMtdGVjaC02LTEuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib">Figure 1 Edu Tech: Using the latest technology to bring innovation to educational methods<h2 id="isPasted">Utilizing technology to maximize human abilities</h2>The term “Edu Tech” is a neologism coined from the words “education” and “technology.” It is said that teacher-student relationships have existed in the workplace since pre-history, and up until the present day the transfer of knowledge and skills from a person who guides to a person who learns has formed the foundation of education. In fact, in primary and secondary school education, in personal training in the workplace, and in fields such as sports and the arts, the teacher or coach providing guidance to the learner has been the common theme.The goals of Edu Tech can be divided into two major categories (Figure 2).<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzAwMTA0NTkwODAyLXZhcmlvdXMtdGVjaC02LTJfZW4ucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib">Figure 2 The two goals of Edu TechThe first is to provide more people with learning opportunities for maximizing individual abilities and expanding possibilities.Acquiring knowledge and skills is a process that takes considerable time. But nowadays it is difficult for busy people, whether young or old, male or female, to set aside substantial blocks of time to study. If technology can be used to enable individuals to flexibly devote time between other tasks or on days off to study, the available learning opportunities can be increased.Furthermore, if we compare urban areas with well-equipped education infrastructure and rural areas that lack such infrastructure, there is a disparity in the subjects and methods available for study. Even though education is the most effective way to eliminate poverty, which is one of the sustainable development goals (SDGs), there are many people throughout the world who lack educational opportunities. If ICT can be put to use enabling people to receive instruction, educational opportunities will become more flexible, and the likelihood of overcoming the problem of unequal opportunity will increase.Another goal is to enhance the effectiveness and efficiency of education by providing individualized instruction customized to match the specific characteristics of each learner and the state of their educational progress. When large numbers of students are all taught the same material using the same methods, it is inevitable that some students will find classes insufficiently challenging while others will have difficulty keeping up and eventually fall behind.One reason that a uniform approach to education has been the norm until now is that the number of teachers is much smaller than the number of students. If technology makes it possible to carefully monitor factors such as the progress, ability, and personality of each individual student and to tailor the instruction to match, perhaps slumbering talent will blossom, and students will awaken to new possibilities they were not aware of and will be able to acquire knowledge and skills more effectively.<h2>Expanding applications of Edu Tech in schools, workplaces, and fields such as sports and the arts</h2>Some specific examples of how Edu Tech can be applied in new ways to education and training in schools, workplaces, and a variety of industries are presented below (Figure 3).<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNzAwMTA0NjE2NzQ4LXZhcmlvdXMtdGVjaC02LTNfZW4ucG5nIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 766px;" class="fr-fic fr-dib">Figure 3 Expanding applications for Edu TechOur first example is the application of Edu Tech in primary and secondary education. In March 2019, Japan launched the “Global and Innovation Gateway for All (GIGA) School Project,”*1 which aims to promote the training of young people able to meet the demands of the future by distributing a computer terminal to each and every elementary and secondary school student in the country. This initiative is intended to realize an educational environment that encourages the individuality of each student and promotes creativity optimized to each learner. Tablet computers that can connect to the network via a cellular or Wi-Fi® link are used to enable close sharing in the learning process between each student and the teacher as lessons proceed.In the past, classes usually proceeded in a style characterized by the teacher speaking from a podium at the front of the classroom, with a few students occasionally answering questions the teacher put to them. By using tablets, the teacher and all the students can share in the taking of notes by individual students or the process of figuring out answers to questions. This has made it possible not only for the teacher to see which students got the right answer, but also for everyone to share the train of thought leading to the answer, for individual students to help each other, and for the proficiency level of the entire class to rise. What’s more, using the camera functionality, students can do things like summarizing the results of their observations in science class or dynamically expressing their thoughts in videos they shoot and edit themselves, thereby developing their ability to make presentations.Our second example involves the use of Edu Tech by a company in the manufacturing industry to quickly get new employees up to speed on factory procedures currently being performed by experienced workers. In factories where a wide variety of products are produced in small quantities, with many different products being produced on the same line, substantial variations in production efficiency and the quality of finished products can arise due to differences in the skill level of the workers. The most skilled workers have learned through experience how to perform operations precisely and without wasted effort. Since their know-how and skills are hard to express in writing, it can be difficult to convey the key points and tricks of the trade to the newer workers.There are now companies that use cameras to capture the work of experienced employees and their actions on the line. Motion tracking technology is then used to convert the videos into digital data, and AI analysis is employed to determine which actions can be linked to improvements in productivity and quality. Key points for improving skills can then be presented in visual form and used in the training of new workers. Training workers using materials incorporating visualized information, and monitoring the actions of the workers undergoing training and providing feedback in real time make it possible for new employees to attain the same level of skill as the experienced workers much more quickly.Our third example involves technology currently in the research stage. It uses Edu Tech to allow learners to experience the techniques of skilled individuals in areas such as crafts, the arts, and sports, enabling them to improve their skills effectively and rapidly. In one method of teaching the subtle aspects of using a brush in painting or Japanese calligraphy, the student holds the brush and the teacher grasps the student’s hand in order to demonstrate aspects such as the correct application of pressure and the experience of moving the brush. A similar method of instruction is often used in the world of sports, where the learner is assisted by the coach and helped to experience the correct posture and movements. By conveying the sense felt only by one who has mastered the skill, the learner is enabled to achieve mastery quickly. This method of teaching can be very effective, but it requires one-on-one training of the learner by an experienced instructor and therefore cannot be easily adopted by everyone.Technology currently under development utilizes new technologies such as virtual reality (VR), haptic feedback, motion tracking, and robotics to convert the body posture and movements of the instructor into digital data and then convey them to the learner. For example, there is already technology that reproduces using a robot arm the subtle movements and application of pressure of an expert Japanese calligrapher. By using this technology to store the brush manipulation of the master as digital data, it can then be reproduced anywhere and at any time for practice.Education is said to be the surest and most effective investment we can make. It is also indispensable to the continued development of society necessary for a happy human life. Some people worry that the advancement of AI and robots will deprive people of their jobs. But depending on how it is used, technology can expand human possibilities and encourage human growth. The fuller adoption of Edu Tech will surely lead to the advancement of humankind.<hr>*1 The GIGA School Project is an Initiative of the Japanese Ministry of Education, Culture, Sports, Science and Technology that aims to create an environment in which ICT terminals such as PCs and tablets can be used effectively for education in venues such as elementary, junior high, and senior high schools. GIGA stands for “Global and Innovation Gateway for All.” It promotes innovation in the educational space through efforts that go beyond the provision of hardware to include the provision of software such as digital textbooks and AI-based drills concentrating on areas where the student is weak, and the strengthening of an instruction system utilizing outside input such as requests from local instructors and assistance from ICT support personnel.<hr id="isPasted"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1700104672958-1700104672958.png" class="fr-fic fr-dii">If you have any questions based on this article that you would like to discuss with an expert at Murata, don't hesitate to reach out. There's an entire team ready to support you with your question.<a href="https://www.murata.com/en-eu/contactform?&Detail=Wevolver%20request" target="_blank" rel="nofollow" class="button-main-action">GET IN TOUCH</a>

Here we describe a movement known as “Edu Tech” that encourages the development of new technology to bring about major changes in educational methods

Fostering Individuality and Bridging Educational Inequality: The Impact of EduTech

This article was discussed in our <a href="https://www.wevolver.com/profile/the.next.byte" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/94de5079-b574-4a3f-8251-3be6800d1ac5?dark=false" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe> The full article will continue below.<hr>Connectomics, the ambitious field of study that seeks to map the intricate network of animal brains, is undergoing a growth spurt. Within the span of a decade, it has journeyed from its nascent stages to a discipline that is poised to (hopefully) unlock the enigmas of cognition and the physical underpinning of neuropathologies such as in Alzheimer’s disease.&nbsp;At its forefront is the use of powerful electron microscopes, which researchers from the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Samuel and Lichtman Labs of Harvard University bestowed with the analytical prowess of machine learning. Unlike traditional electron microscopy, the integrated AI serves as a “brain” that learns a specimen while acquiring the images, and intelligently focuses on the relevant pixels at nanoscale resolution similar to how animals inspect their worlds.&nbsp;“<a href="https://www.biorxiv.org/content/10.1101/2023.10.05.561103v1.abstract" target="_blank">SmartEM</a>” assists connectomics in quickly examining and reconstructing the brain’s complex network of synapses and neurons with nanometer precision. Unlike traditional electron microscopy, its integrated AI opens new doors to understand the brain's intricate architecture.The integration of hardware and software in the process is crucial. The team embedded a GPU into the support computer connected to their microscope. This enabled running machine-learning models on the images, helping the microscope beam be directed to areas deemed interesting by the AI. “This lets the microscope dwell longer in areas that are harder to understand until it captures what it needs,” says MIT professor and CSAIL principal investigator Nir Shavit. “This step helps in mirroring human eye control, enabling rapid understanding of the images.”&nbsp;“When we look at a human face, our eyes swiftly navigate to the focal points that deliver vital cues for effective communication and comprehension,” says the lead architect of SmartEM, Yaron Meirovitch, a visiting scientist at MIT CSAIL who is also a former postdoc and current research associate neuroscientist at Harvard. “When we immerse ourselves in a book, we don't scan all of the empty space; rather, we direct our gaze towards the words and characters with ambiguity relative to our sentence expectations. This phenomenon within the human visual system has paved the way for the birth of the novel microscope concept.”&nbsp;For the task of reconstructing a human brain segment of about 100,000 neurons, achieving this with a conventional microscope would necessitate a decade of continuous imaging and a prohibitive budget. However, with SmartEM, by investing in four of these innovative microscopes at less than $1 million each, the task could be completed in a mere three months.<h2>Nobel Prizes and little worms &nbsp;</h2>Over a century ago, Spanish neuroscientist Santiago Ramón y Cajal was heralded as being the first to characterize the structure of the nervous system. Employing the rudimentary light microscopes of his time, he embarked on leading explorations into neuroscience, laying the foundational understanding of neurons and sketching the initial outlines of this expansive and uncharted realm&nbsp;— a feat that earned him a Nobel Prize. He noted, on the topics of inspiration and discovery, that “As long as our brain is a mystery, the universe, the reflection of the structure of the brain will also be a mystery.”Progressing from these early stages, the field has advanced dramatically, evidenced by efforts in the 1980s, mapping the relatively simpler connectome of <a href="https://www.nature.com/articles/s41586-021-03778-8" target="_blank">C. elegans</a>, small worms, to today’s endeavors probing into more intricate brains of organisms like zebrafish and mice. This evolution reflects not only enormous strides, but also escalating complexities and demands: mapping the mouse brain alone means managing a staggering thousand petabytes of <a href="https://www.cell.com/cell/pdf/S0092-8674(20)31001-1.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">data</a>, a task that vastly eclipses the storage capabilities of any university, the team says.&nbsp;<h2>Testing the waters</h2>For their own work, Meirovitch and others from the research team studied 30-nanometer thick slices of octopus tissue that were mounted on tapes, put on wafers, and finally inserted into the electron microscopes. Each section of an octopus brain, comprising billions of pixels, was imaged, letting the scientists reconstruct the slices into a three-dimensional cube at nanometer resolution. This provided an ultra-detailed view of synapses. The chief aim? To colorize these images, identify each neuron, and understand their interrelationships, thereby creating a detailed map or “connectome” of the brain's circuitry.“SmartEM will cut the imaging time of such projects from two weeks to 1.5 days,” says Meirovitch. “Neuroscience labs that currently can't be engaged with expensive and long EM imaging will be able to do it now,” The method should also allow synapse-level circuit analysis in samples from patients with psychiatric and neurologic disorders.&nbsp;Down the line, the team envisions a future where connectomics is both affordable and accessible. They hope that with tools like SmartEM, a wider spectrum of research institutions could contribute to neuroscience without relying on large partnerships, and that the method will soon be a standard pipeline in cases where biopsies from living patients are available. Additionally, they’re eager to apply the tech to understand pathologies, extending utility beyond just connectomics. “We are now endeavoring to introduce this to hospitals for large biopsies, utilizing electron microscopes, aiming to make pathology studies more efficient,” says Shavit.&nbsp;Two other authors on the paper have MIT CSAIL ties: lead author Lu Mi MCS ’19, PhD ’22, who is now a postdoc at the Allen Institute for Brain Science, and Shashata Sawmya, an MIT graduate student in the lab. The other lead authors are Core Francisco Park and Pavel Potocek, while Harvard professors Jeff Lichtman and Aravi Samuel are additional senior authors. Their research was supported by the NIH BRAIN Initiative and was presented at the 2023 International Conference on Machine Learning (ICML) Workshop on Computational Biology. The work was done in collaboration with scientists from Thermo Fisher Scientific.

MIT researchers invented a technology and software to take electron microscopy to the next level by seamlessly integrating real-time machine learning into the imaging process — “smart microscopy.” Left image: Yaron Meirovitch via the Stable Diffusion XL AI image generator and Alex Shipps via the Midjourney AI image generator. Right image: Daniel Berger and Meirovitch, edited by Alex Shipps/MIT CSAIL

MIT CSAIL researchers combine AI and electron microscopy to expedite detailed brain network mapping, aiming to enhance connectomics research and clinical pathology.

Using AI to optimize for rapid neural imaging

Science fiction films portray the idea relatively simply: the terminator – who either tries to destroy or rescue humanity – is such a perfect humanoid robot that in most cases it is superior to humans. But how well do humanoid robots perform nowadays away from the cinema screen? Precisely this question is addressed by a new study drawn up by lead author Robert Riener, Professor of Sensory-Motor Systems at ETH Zurich and founder of the <a href="https://cybathlon.ethz.ch/en" target="_blank">Cybathlon</a>, that is being published today in the robotics journal Frontiers in Robotics and AI. &nbsp;<iframe width="640" height="360" src="https://www.youtube.com/embed/u9nKDxvTMeY?&amp;wmode=opaque&amp;enablejsapi=1&amp;origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true">&nbsp;&nbsp;&nbsp;&nbsp;</iframe>Digit is a humanoid robot designed to move more dynamically than conventional robots. (Video: Agility Robotics)<h2>Comparing apples with apples</h2>The first scientific challenge was to develop criteria that permit a meaningful comparison between humans and machines. An industrial robot painting car bodies on a production line does this faster, for longer and more precisely than a human. It is especially developed for this but also does not have any other abilities.Riener therefore excluded such robots from the study: “We humans shape our environment according to our criteria and needs. If robots are to support us in a meaningful way, they need to work in this manmade environment. We therefore quickly arrived at robots that are similar to humans, at least anatomically.” It is for this reason that Riener exclusively examined humanoid robots for the study and integrated 27 relevant specimens into his research.Yet the researchers also defined certain selection criteria within this robot type. “For example, for a robot that has rollers rather than legs it would be fairly easy to roll faster than a human can run – but we didn’t want to compare apples with pears,” explains Riener. Only those robots were therefore selected that had two or four legs so that they were also able to climb steps. They also need to have a slim figure in order to pass through doors, and a certain height (at least 50 cm) with arms and hands (or extendable by arms and hands) so that they can also pick up objects on a tray or shelf. In order to be able to work with and support humans, they should also be quiet and not give off any exhaust emissions. &nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699581467325-image1.imageformat.lightbox.1055172521.jpg" style="width: 766px;" class="fr-fic fr-dib">ANYmal is a four-legged robot for the inspection and maintenance of technical systems. (Photograph: Robotic Systems Lab / ETH Zurich)<h2 id="isPasted">Robots clearly better – in terms of components</h2>The initial result surprised even the researcher: if one compares the individual components of machines and humans such as microphones with ears, cameras with eyes or drive systems with muscles, the technical components always fare better in terms of key sensory-motor properties. These days, for instance, carbon fibres are used, which are harder than bones. If we disregard other properties of the human bone, such as the fact that it is self-healing, the technical solution is clearly superior in terms of mechanical features. The baffling thing, as the ETH professor explains, is as follows: “The question that arises is why we are not able today to construct a robot from these high-quality components that has better powers of movement and perception than humans.”Which brings us to the second result of this comprehensive study: if we consider the activities that humans and machines are asked to carry out, humans are generally superior to robots. Although humanoid robots are also able to walk and run, if we set walking or running speed in relation to body dimensions, weight or energy consumption, most robots are no longer able to keep pace. At 6.1 metres per second, robot MIT-Cheetah runs faster than a jogging human and accordingly lives up to its name. However, the four-legged robot has a high energy consumption (973 watts) and is also only deployed under laboratory conditions. Humans also significantly outperform robots in terms of endurance versus operating time. &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp;<h2>Karate Kid with stiff joints<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699581515083-image.imageformat.textdouble.19354851.jpg" style="width: 304px;" class="fr-fic fr-dib">Humanoid iCub in child size from 2009. (Photograph: IIT-Istituto Italiano di Tecnologia)</h2>Robots benefit for certain functions from their precision. “For example, when balancing on one leg, robots can easily stiffen their joints, while humans tend to wobble a bit – which costs considerably more energy. Robots can also precisely recognise their joint angles and repeat movements very accurately, which is pretty impressive and somewhat reminiscent of Karate Kid,” says Robert Riener.The results are more mixed for another movement function – picking up objects: while robots can pick up objects extremely quickly, they are not yet able to outdo us regarding our many different hand movements and the manipulative skills of our fingers. And another weakness of robots emerges with regard to various movements such as swimming, crawling and jumping as they are only able to perform some of these movements. By contrast, most humans are easily capable of performing and combining several of these movements. Playing football is cited in the new study as an example of this: machines are still a long way from dribbling, heading or analyse and interprete the strategy of the other players. &nbsp;&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699581594040-1699581594040.png" style="width: 766px;" class="fr-fic fr-dib"><h2 id="isPasted">Robots can support us in the future</h2>Are humanoid robots today therefore still just a gimmick? “No, the progress made by robotics in recent years is incredible. We wish to have robots around us so that they can help us with difficult or dangerous tasks. However, our manmade environments are very complex, and it’s therefore not so easy for robots to function here autonomously and without error. Nevertheless, I’m confident that with the powerful technical components that are available we will soon be able to construct more intelligent robots that are capable of interacting with us humans better,” says Riener. An important next step according to Riener is to go to greater lengths in terms of system engineering and automatic control technology in order to combine the existing powerful components better.Deployment would then be conceivable, for example, in nursing and home care, the construction industry or in the household – i.e. wherever support is urgently needed in order to relieve staff and to support people with limited mobility, for instance.<hr><h2 id="isPasted">Reference</h2>Riener, R., Rabezzana, L., Zimmermann, Y: Do Robots Outperform Humans in Human-Centered Domains? Frontiers, Volume 10, November 2023, doi: <a href="https://www.frontiersin.org/articles/10.3389/frobt.2023.1223946/abstract" target="_blank">external page10.3389/frobt.2023.1223946</a>

A new ETH study compares 27 humanoid robots with humans and comes to the conclusion that while robots have better components, they are still not capable of achieving as much. However, according to the authors of the study, the machines are catching up.

Humans are far superior to robots

This article is based on an article titled, <a href="https://cambrian-ai.com/wp-content/uploads/2023/08/BrainChip-Sees-Gold-Final_2.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">BrainChip Sees AI Gold in Sequential Data Analysis at the Edge</a>, from the Cambrian AI website.Amidst the whirlwind of excitement surrounding Large Language Model (LLM) generative AI, it's easy to lose sight of other AI domains that have seemingly dissolved into the shadows cast by ChatGPT's prominence. One underappreciated domain is the analysis of sequential data streams, which includes monitoring fluctuating stock prices and interpreting video feeds.&nbsp;BrainChip has identified this niche — the adept handling of sequential data — as a pivotal niche for deploying its Akida technology. Akida stands out for its prowess in Event-Based Neuromorphic computing, adeptly handling various neural network architectures like Vision Transformers (ViT), Convolutional Neural Networks (CNN), Temporal Evolution Network (TENN), and Recurrent Neural Networks (RNN).&nbsp;This article explores the need for efficient edge AI for time-series data.<h2 dir="ltr">Sequential data analysis</h2>Sequential analysis refers to the process of analyzing and extracting insights from data that is collected and organized in chronological order. This data type typically involves measurements or observations taken at regular intervals over time. Time-series analysis techniques aim to understand data patterns, trends, and dependencies and make predictions or forecasts based on historical patterns.A few use cases of sequential data analysis include:1. Financial Analysis: Time-series analysis is extensively used in finance to study stock market trends, analyze economic indicators, and forecast future market conditions. It helps model asset prices, trends, risk assessment, and portfolio optimization.2. Demand Forecasting: Sequential analysis is crucial in demand forecasting for retail, supply chain management, and manufacturing industries. By analyzing historical sales or demand data, businesses can predict future demand patterns and optimize their production, inventory, and supply chain accordingly.3. Predictive Maintenance: Predictive maintenance can monitor equipment and machinery in real-time. Analyzing sensor data and historical patterns can help detect anomalies and predict potential failures, enabling proactive maintenance and minimizing downtime.As well as applications in Energy Consumption Analysis and IoT Sensor Data Analysis.The market size for applying AI in time-series data analysis is continually growing as organizations recognize the value of extracting insights and making accurate predictions from temporal data. While specific market size figures for this realm are not readily available, the broader AI market, including applications in time-series analysis, is expected to grow substantially. According to a report by Grand View Research, the global AI market size was valued at USD 62.35 billion in 2020 and is projected to expand at a compound annual growth rate (CAGR) of 40.2% from 2021 to 2028. This growth encompasses various AI applications, including time-series analysis, across multiple industries.<h1 dir="ltr">Introducing the Dimension of Time to Neural Networks</h1>Traditional CNNs have been around for 30+ years and combine multiple hidden layers trained in a supervised manner. These are sequential and hence referred to as feed-forward neural networks. Bi-directional networks, also called RNNs, invented at the turn of the century, added capability for more complex learning, such as language modeling. But for applications to time series, a machine learning engineer needed a combination of CNNs and a temporal network for spatial-temporal analysis. While academia developed networks that did temporal convolution, they have yet to be power efficient or easy to train to make it to the far Edge.<h1 dir="ltr">Temporal Event-based Neural Networks</h1>Temporal Artificial Neural Networks (TENNs). This approach simplifies training and reduces model size while maintaining accuracy, resulting in improved performance and efficiency for Edge AI devices.Using TENNs for data analysis offers several advantages, such as the ability to learn the temporal structure of the data, which is crucial for tasks such as forecasting and anomaly detection. TENNs can make predictions for future time steps, and they are capable of learning from large datasets of time series data. Overall, these features make TENNs a valuable tool for data analysis in various domains.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699529042393-image3.png" style="width: 300px;" class="fr-fic fr-dib">Traditional time series analysis applies to all kinds of signals. Image credit: Cambrian AIBeyond traditional Edge time series applications, BrainChip suggests that TENNs could minimize or eliminate the need for DSP filtering of raw audio signals and vital signs in health monitoring. Thus, offering compact solutions for wearable, hearing, and implantable devices with minimal power consumption is a significant advance for preventative healthcare.Additionally, TENNs also excel at treating streaming inputs as a time series of frames, performing 3D convolutions composed of a temporal convolution on the time axis and a spatial convolution on the XY axis. This is efficiently achieved to improve the detection of higher-resolution video objects in low-power scenarios.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699529079641-image2.png" style="width: 300px;" class="fr-fic fr-dib">Treating streaming inputs as a 3D time series of frames with a highly efficient 3D convolution. Image credit: Cambrian AI.TENNs offer developers the flexibility to configure them in either buffered temporal convolution or recurrent modes, enabling them to adapt the network to their specific application requirements. Furthermore, TENNs can be efficiently trained on parallel hardware, such as GPUs and TPUs in the cloud, similar to convolutional networks, while retaining the compactness of RNNs for efficient inference at the edge. This approach helps to minimize the exponentially growing cost of training, which is a constant concern.<h1 dir="ltr">Akida 2nd&nbsp;Generation Processor and TENNs</h1>The BrainChip Akida processor is a digital portable processor IP inspired by the energy-efficient functionality of the human brain. Unlike traditional neuromorphic approaches, which are analog, it utilizes fully digital technology and offers a range of capabilities, including image classification, semantic segmentation, odor recognition, and time-series analysis. It supports various neural network architectures, including TENNs.The Akida processor utilizes highly parallel event-based neural processing cores, merging neuromorphic processing with native support for traditional convolutional capabilities and functions, along with hardware support for TENN networks. Its neuromorphic processing cores communicate using sparse, asynchronous events, making it ideal for efficient time-series data analysis and managing high-speed, asynchronous, and continuous data streams.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699529133867-image4.png" style="width: 300px;" class="fr-fic fr-dib">The TENN operation may combine transform from convolutions in training to recurrence operation for inference. Image credit: Cambrian AI.BrainChip’s Akida allows the analysis of vision, video, and three-dimensional data as a time series, improving video object detection. Akida's support for spatial-temporal convolutions enhances speed and reduces energy consumption. This ability is possible because the processor features a high-speed, low-power digital design optimized for edge computing applications, offering real-time processing and low-latency analysis. It can handle structured and unstructured data, learning and recognizing patterns from streaming data, making it suitable for time-series data analysis.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699529192601-image4.png" style="width: 300px;" class="fr-fic fr-dib">The foundations of the Akida architecture. Image credit: Cambrian AI.Additionally, Akida includes a traditional CNN accelerator, as well as TENN and ViT logic, providing a comprehensive solution for sequential processing. The Akida processor is particularly effective for real-time data classification, anomaly detection, and predictive analytics. Consequently, the second-generation Akida processor, with TENN support, extends its efficiency and accelerated hardware solutions to multi-dimensional applications like video object detection and vision using event-based processing paradigms.<h1 dir="ltr">Conclusion</h1>The rapid expansion of the AI field has primarily focused on image processing and LLMs, leaving a significant gap in the development of sequential data analysis. BrainChip's Akida technology, featuring TENNs, simplifies training, reduce model size, and enhance performance and efficiency in time series data analysis.&nbsp;This innovative approach can be applied in different industries, including finance, demand forecasting, predictive maintenance, energy consumption analysis, and IoT data analysis, meeting the growing demand for effective AI solutions in these domains. The Akida processor extends its efficiency to multi-dimensional applications improving real-time data analysis, predictive analytics, and video object detection for event-based processing.

How BrainChip's Akida technology is revolutionizing time series data analysis.


The huge potential of sequential data analysis at the edge

For retailers, selling commodities, apparel, home appliances, etc., the amount of consumer information you collect greatly affects sales. Unless you accurately assess what customers want now and stock up on inventory during the optimal period when they are required, in the optimal quantities and at the lowest possible cost, you cannot grow your revenue. To succeed in the retail industry, it is an absolute requirement that you develop the ability to discern customer needs.The retail industry has a long history of continuously developing technologies and business methods for handling customers and products, developing distribution strategies, and managing various other types of information. The industry has always adopted the latest up-to-date information processing technology. Here, we explain the movement called “retailtech,” which develops and uses the latest information technologies and has become widely used in the retail industry.<h2>Individually supporting diversifying consumer needs with digital technologies</h2>Retailtech is a term that combines “retail,” representing the retail industry, and “technology.” It means the incorporation of artificial intelligence (AI), IoT, and other leading-edge IT technologies into the collection and analysis of customer information, the management of distribution and inventory, settlement, etc. to increase their effectiveness and efficiency. Broadly speaking, robots that help with sales, robots that pick products to be delivered at distribution centers, and the shift to cashless settlement, etc. are also included in retailtech.Since the start of the 21st century, the environment surrounding the retail industry has dramatically changed.First, the sense of values, interests, and preferences of consumers have diversified due to market globalization and the filter bubble effect*1 due to the expanded use of search engines, social networking services, and other Internet environments. As a result, it is becoming necessary to not only to grasp what is selling in the consumer market overall, but also to discern what items individual customers need and sell such items to them separately.*1 The filter bubble effect refers to the phenomenon in which consumers are only able to see the information that they wish to see on the Internet. By continuing to collect and accumulate only information that matches their preferences without coming into contact with information that does not match their sense of values, individual consumers strengthen the tendency to develop radical preferences that are biased in a specific field only, and it is believed that diversification increases as a result.Moreover, the information for retail shops to gain insight into customers is being digitized, and the location of commerce is shifting from real sales floors to Internet sites, which is a significant change. The digitization of customer information that started a long time ago from POS systems*2 and the point cards issued by mass-market retailers is further evolving with the current spread of online shopping. Now, artificial intelligence (AI) analyzes user registration information, their search history on the Internet, and on-site behavior history to discern individual interests and preferences, what products they currently want, and the amount they might be able to pay to purchase a product. Furthermore, retail methods that propose products that individual consumers might want at the optimal time have become commonplace.*2 A POS (Point of Sales) system scans the barcode attached to a product when sales are made at the cash register on the sales floor to manage what products were sold when and where. It is used to collect information for effectively managing products, inventory, and customers.The use of digital technologies is essential to individually responding to diversified consumer needs. If you are a skilled marketer, changes in market trends can be picked up from market information using your experience and sense. However, a person cannot make decisions about the individual needs and desired products for a massive number of consumers. Therefore, the use of AI and other forms of IT to replace the skills of a marketer and respond to individual consumers as needed becomes essential.<h2>Integrating brick-and-mortar stores and online stores in order not to miss a targeted customer</h2>In recent years, the movement to integrate online sales and product sales at brick-and-mortar stores by using the latest technologies is becoming apparent in the retail industry. This sales method, which collects customer information through multiple channels and aims to build a mechanism that can sell according to the method desired by each customer, is called “OMO” (Online Merges with Offline) (Figure 1).<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699267693485-various-tech-8-2en.png" style="width: 766px;" class="fr-fic fr-dib">Figure 1 Utilize IoT to integrate customer information from brick-and-mortar and online storesSince the start of the 21st century, measures have rapidly developed to increase sales at online stores. However, brick-and-mortar stores and online stores each have their advantages and disadvantages. To increase the degree of satisfaction without missing a customer, it is more rational to separately use the characteristics of both types of stores according to customers’ needs. Therefore, the number of retail companies that are advancing attempts to utilize IoT to make it possible to collect the kind of detailed customer information that is collected online at brick-and-mortar stores is increasing in recent years.Two technologies that are being utilized in various applications as a means to follow the movements of store customers and products within a brick-and-mortar store and collect customer information are image recognition and RFID*3 tags (Figure 2).<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699267714710-various-tech-8-3.jpg" style="width: 766px;" class="fr-fic fr-dib">Figure 2 Collecting customer information with RFID, etc. and providing a high-quality customer experience with AR, etc. A product with an RFID tag attached (left) and utilizing AR to consider a furniture purchase (right)*3 RFID (Radio Frequency Identification) is a technology that uses radio waves to read and write data without contact. By attaching a small semiconductor chip that stores an RFID mechanism and information as a tag to each individual product, it becomes possible to carry out fine-grained management of products by reading and writing information with RFID as needed.Retail shops that have installed a large number of cameras, various sensors, microphones, and RFIDs, etc. and introduced IoT systems with AI that analyzes in real time what store customers picked up. The customer information that was collected with previous POS systems and point cards could not be collected unless a customer actually purchased a product. By utilizing such IoT systems, it becomes possible to know what products a store customer was comparing and what they ultimately bought.If you utilize information collected in this way, you can take various measures such as sending special deal information to customer smartphone apps to give them a push, providing a reminder several days later about a product that they were interested in but did not purchase, optimizing the types, placement location, and flow lines of products displayed in the store in order not to miss customers. Moreover, if you install sensors on the product shelves and attach RFID tags to the products, you will become able to assess the product display conditions in real time to enable efficient sales that never miss a business opportunity through highly precise inventory management and just-in-time product replenishment.In addition, it also became possible to identify the products to purchase and smoothly complete the checkout process just by placing the shopping basket in the designated location at the self-checkout terminal and scanning the RFID tags attached to the products. For store customers who created an account in advance at a cutting-edge store, it is even possible to automatically check out when carrying goods out of the store even if you do not pay at the register. With such mechanisms, the stress of waiting for the register will be eliminated.<h2>Providing a high-quality customer experience utilizing AR and VR</h2>Some retail stores are introducing systems that utilize augmented reality (AR) technology to provide assistance in selecting a product to purchase or to make accurate suggestions about how to use a product or what product to purchase on that occasion.For example, there is a mass furniture retailer that provides an AR app that enables users to check on a smartphone or tablet device display what a piece of furniture they are thinking about purchasing would look like when actually placed in their own room. The impression given off by a piece of furniture changes considerably from the showroom to the location where it is actually placed. Depending on the situation, it may be too large to get into the room. By utilizing an AR app, you can avoid making the wrong choice and shop with a high degree of satisfaction. In the future, it might become possible to utilize virtual reality (VR) with haptic technology, etc. to check how a sofa feels, etc. online.There are also supermarkets providing AR apps that can display the basic ingredients, place of production, allergens, etc. of products lined up in the food section. Recently, there are also stores creating systems that present cooking recipes using those ingredients or the seasonings needed to make a dish so that you can purchase them together.In the retail industry, entertainment that moves people is required by sensitively perceiving the customer’s emotions and preparing the expected services in advance. All consumers want to enjoy their shopping. Going forward, more advanced forms of retailtech will appear one after another and likely provide new forms of enjoyment to consumers.<hr id="isPasted"><img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1699267752774-1699267752774.png" class="fr-fic fr-dii">If you have any questions based on this article that you would like to discuss with an expert at Murata, don't hesitate to reach out. There's an entire team ready to support you with your question.<a href="https://www.murata.com/en-eu/contactform?&Detail=Wevolver%20request" target="_blank" rel="nofollow" class="button-main-action">GET IN TOUCH</a>

Here, we explain the movement called “retailtech,” which develops and uses the latest information technologies and has become widely used in the retail industry.

Revolutionizing Retail: Creating Dynamic Customer Experiences through Advanced RetailTech

In engineering, quality control ensures the reliability, safety, and consistency of products and processes. As industries evolve, the demand for continual improvement becomes paramount, not just to stay competitive but also to guarantee the highest standards of safety and reliability. In this dynamic landscape, the introduction of Edge AI emerges as a transformative solution, poised to revolutionize quality control mechanisms.Quality control, especially in engineering environments, is not just about maintaining standards; it's about elevating them. The competitive nature of today's industries necessitates a relentless pursuit of perfection. Traditional methods, while effective, often need more agility and real-time responsiveness than modern manufacturing and production environments require. This is where the need for continual improvement and innovation comes into play.Edge AI, a technology that emphasizes processing data at its origin rather than relying on a centralized data center, presents a sophisticated advancement in quality control. By integrating AI capabilities directly into devices and systems on the manufacturing floor, Edge AI facilitates real-time analysis, immediate feedback, and rapid decision-making. Such capabilities are not just enhancements; they are transformational, enabling businesses to detect anomalies, predict issues, and ensure optimal quality at unprecedented speeds.Drawing insights from various industry studies and advancements, it's evident that Edge AI's integration into quality control processes offers a promising avenue for industries to stay ahead, ensuring both competitiveness and unparalleled quality standards.Let's delve deeper!<iframe width="540" height="600" src="https://c8056756.sibforms.com/serve/MUIFAMyA6BGksOUPEokHuBnEmZRHhYgJ4RXb4BV0gvzN98ymNIvQdTcBFQnRVfviT6yZSFW_R2g1hENBu7p7Afnyv9Kt0unAAbfFU5mMQhBwI-8hQnKf2r1mmRKhUgDLmtk8bpVSZ7kZGpleCPqtYRv8_kkvODL7F4neGLNGgdpFDm9pPzoYpwbQkc0BU5GVOFoq8CSmD0DDvDjG" frameborder="0" scrolling="auto" allowfullscreen="" style="display: block;margin-left: auto;margin-right: auto;max-width: 100%;" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> <h2 dir="ltr">The Imperative of Quality Control in Engineering</h2>Quality control has traditionally been a reactive process, heavily reliant on post-production inspections and tests. Traditional methods, while foundational, have their limitations:Traditional Quality Control Systems: Historically, quality assurance has been downstream-focused, emphasizing production and testing. This approach, often characterized by repetitive design-prototype-test cycles, can be likened to a trial-and-error method. Such methods might only sometimes yield optimal designs, leading to increased costs, extended cycle times, and potential compromises in customer quality.&nbsp;The traditional system operates on the premise that as long as a product is within specification limits, it meets customer requirements. However, the business implications of a product being "barely within specification limits" and "right on target" are vastly different.Financial and Operational Implications: Inadequate quality control can have severe financial repercussions. Products that don't meet quality standards can lead to recalls, warranty claims, and loss of customer trust. Operationally, inadequate quality control can result in increased wastage, rework, and delays in production schedules.Evolving Standards and Expectations: With the rapid advancements in technology and globalization, industry standards are continually evolving. Customers today are more informed and have higher expectations. They demand products that are functional but also safe, durable, and innovative. This drives the need for more robust and proactive quality control processes.The limitations of traditional quality control methods and the changing landscape of customer expectations underscore the need for innovative solutions. As industries strive for perfection, there's a pressing demand for methods that are reactive but also proactive, predictive, and efficient.<h2 dir="ltr">The Advent of Edge AI in Quality Control</h2>As traditional methods have inherent limitations, the industry is turning to innovative solutions such as Edge AI.Edge AI refers to deploying artificial intelligence algorithms directly on the devices where data is generated rather than processing this data in a centralized cloud-based system. This proximity to the data source facilitates real-time data processing, ensuring swift responses and immediate insights.<h3 dir="ltr">Addressing Traditional Limitations</h3>Traditional quality control methods, while foundational, often lag in real-time responsiveness and agility. Edge AI, with its on-device processing capabilities, addresses these gaps. By analyzing data at the source, it eliminates the latency associated with transmitting data to a central server for processing. This not only speeds up the quality control process but also enhances its accuracy and efficiency.<h3 dir="ltr">Benefits of Edge AI in Quality Control</h3>Real-time Anomaly Detection: With Edge AI, anomalies in the manufacturing or production process can be detected in real-time, allowing immediate corrective actions.Predictive Maintenance: Edge AI can predict equipment failures before they occur, ensuring uninterrupted operations and reducing downtime.Reduced Operational Costs: By processing data locally, Edge AI reduces the need for data transmission and cloud storage, leading to potentially significant cost savings. Additionally, the efficiency gains from real-time insights and predictive maintenance further contribute to operational cost reductions.Integrating Edge AI into quality control processes signifies a monumental shift from reactive to proactive quality assurance. As industries continue to evolve, technologies like Edge AI will play a pivotal role in ensuring that quality remains at the forefront of all operations.<h2 dir="ltr">Spotlight on Edge Impulse</h2>In the rapidly evolving domain of Edge AI, Edge Impulse stands out as a pioneering platform, offering a comprehensive suite of tools and capabilities tailored for deploying machine learning models on edge devices.Edge Impulse is a cutting-edge platform designed to simplify creating and deploying AI models on edge devices. By providing a user-friendly interface, Edge Impulse allows engineers and developers to harness the power of AI without the complexities often associated with traditional machine learning workflows. One of the standout features of Edge Impulse is its ability to streamline the deployment of machine learning models directly on edge devices.&nbsp;<h3 dir="ltr">Key Features of Edge Impulse</h3>Data Collection: Edge Impulse Studio offers a data acquisition tool that allows users to upload datasets, facilitating the training and validation of machine learning models.Model Training: The platform provides various tools and algorithms, including the YOLOv5 object detection model, which can be optimized for resource-constrained devices.Deployment: After training, Edge Impulse facilitates the deployment of the model on edge devices, such as the <a href="https://www.renesas.com/us/en/products/microcontrollers-microprocessors/rz-mpus/rzv2l-evkit-smarc-som-evaluation-kit-rzv2l-mpu-ai-accelerator" target="_blank">Renesas RZ/V2L Evaluation Board</a>, ensuring seamless integration and real-time performance.Edge Impulse's capabilities extend beyond just quality control in manufacturing. Its versatile platform can be adapted to various applications, making it a valuable tool for industries aiming to leverage the benefits of Edge AI.<h2 dir="ltr">Edge Impulse in Action: A Case Study</h2>Quality inspections are pivotal in ascertaining that products meet the required standards and specifications. A case study involving Edge Impulse offers a deep dive into how cutting-edge technology can elevate these inspections, ensuring optimal product quality.The Challenge: Manufacturers often grapple with establishing a comprehensive inspection procedure encompassing all facets of a product's quality. Traditional methods, while effective, may only sometimes offer the agility and real-time responsiveness required in modern manufacturing environments. The challenge lies in seamlessly integrating the inspection process into the existing workflow without causing disruptions, all while maintaining consistent quality across batches.The Edge Impulse Solution: Solomon Githu, an engineer, envisioned a <a href="https://www.hackster.io/sologithu/product-inspection-with-renesas-rz-v2l-and-edge-impulse-cf0700" target="_blank">solution</a> that would seamlessly integrate into existing processes and autonomously discern product quality. He conceptualized an inspection device employing computer vision and machine learning to inspect products as they traverse an assembly line swiftly.&nbsp;The objective was clear: the device should autonomously determine product quality in milliseconds.To bring this vision to life, Githu leveraged the <a href="https://edgeimpulse.com/product" target="_blank">Edge Impulse Studio</a>. The platform's web-based interface replaced the complexities of traditional machine learning with a user-friendly, point-and-click experience. Using an object detection algorithm, the system was trained to inspect products and discern their quality rapidly. The training involved a dataset comprising both high-quality products and those with defects.To ensure real-time responsiveness, Githu employed the <a href="https://www.renesas.com/us/en/products/microcontrollers-microprocessors/rz-mpus/rzv2l-evkit-smarc-som-evaluation-kit-rzv2l-mpu-ai-accelerator" target="_blank">Renesas RZ/V2L Evaluation Board</a>, specifically designed for computer vision and machine learning applications. Paired with a <a href="https://coral.ai/products/camera/" target="_blank">Google Coral camera</a>, the system was equipped to inspect products and make real-time determinations visually.Outcomes: The system was tested using a custom-built miniature conveyor belt, with printed images of products (in this case, submersible pump impellers) moving along it. The camera, positioned above, relayed real-time visuals to a custom web application, which then displayed the products and maintained a count of the good and defective items it detected. The results were compelling: the system showcased high accuracy, aligning with the impressive performance metrics observed during model training and testing.Conclusion: This case study underscores the transformative potential of Edge Impulse in the realm of quality control. By harnessing the power of Edge AI, manufacturers can elevate their quality inspection processes, ensuring that products not only meet but exceed the desired quality standards.<h2 dir="ltr">The Road Ahead</h2>Integrating Edge AI into quality control processes has showcased transformative results in various engineering domains. As industries continue to evolve and the demand for real-time, efficient, and accurate quality control mechanisms grows, the potential for further integration of Edge AI becomes even more pronounced.Potential Across Engineering Domains:&nbsp;While the manufacturing sector has been an early adopter of Edge AI for quality control, other engineering domains, such as civil engineering, electronics, and aerospace, could benefit immensely from this technology. The ability to process data in real-time at the source can lead to enhanced structural integrity checks, real-time monitoring of electronic components, and swift anomaly detection in aerospace systems.Scalability and Adaptability of Edge Impulse: Platforms like Edge Impulse are designed with scalability and adaptability in mind. Whether adapting to different data types, integrating with various edge devices, or scaling to handle vast amounts of data, Edge Impulse ensures that diverse quality control requirements across industries are met precisely. The platform's capabilities, such as data collection, model training, and deployment, can be tailored to suit specific industry needs, making it a versatile tool for quality control.Meeting Diverse Quality Control Requirements: As industries diversify and products become more complex, the quality control requirements also evolve. Edge AI platforms, with their adaptability, can cater to these diverse needs, ensuring that quality control is not just about meeting standards but setting new benchmarks.<h2 dir="ltr">Conclusion</h2>Integrating Edge AI into quality control processes signifies a significant stride in the engineering domain. Platforms like Edge Impulse have showcased the capability to enhance these processes, offering real-time data processing and decision-making at the source. Such advancements are not just about improving efficiency but also about ensuring consistent and high-quality outputs.Edge Impulse, in particular, has demonstrated its prowess in facilitating the deployment of machine learning models on edge devices. It is a valuable tool for industries aiming to improve quality control mechanisms. Its capabilities, ranging from data collection to model training and deployment, are tailored to meet the specific needs of various industries, ensuring adaptability and scalability.For engineering firms, the message is clear: the future of quality control lies in harnessing the power of Edge AI. By exploring and adopting solutions like Edge Impulse, firms can position themselves at the forefront of technological advancements, ensuring they meet the evolving standards of quality and efficiency in the industry.<iframe width="540" height="600" src="https://c8056756.sibforms.com/serve/MUIFAMyA6BGksOUPEokHuBnEmZRHhYgJ4RXb4BV0gvzN98ymNIvQdTcBFQnRVfviT6yZSFW_R2g1hENBu7p7Afnyv9Kt0unAAbfFU5mMQhBwI-8hQnKf2r1mmRKhUgDLmtk8bpVSZ7kZGpleCPqtYRv8_kkvODL7F4neGLNGgdpFDm9pPzoYpwbQkc0BU5GVOFoq8CSmD0DDvDjG" frameborder="0" scrolling="auto" allowfullscreen="" style="display: block;margin-left: auto;margin-right: auto;max-width: 100%;" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe> <h2 dir="ltr">References</h2><ol><li dir="ltr"><a href="https://metrology.news/re-imagining-manufacturing-quality-with-ai-and-edge-computing/" target="_blank">Re-imagining Manufacturing Quality with AI and Edge Computing</a></li><li dir="ltr"><a href="https://edgeimpulse.com/blog/elevating-quality-standards-with-ai" target="_blank">Elevating Quality Standards with AI</a></li><li dir="ltr"><a href="https://www.griddynamics.com/events/quality-control-manufacturing-webinar-q3-2022" target="_blank">Quality 4.0: Reimagining AI and Quality Control Automation for Smart Manufacturing</a></li><li dir="ltr"><a href="https://developer.ibm.com/articles/enabling-distributed-ai-with-edge-computing/" target="_blank">Enabling Distributed AI for Quality Inspection in Manufacturing with Edge Computing</a></li><li dir="ltr"><a href="https://edgeimpulse.com/blog/elevating-quality-standards-with-ai" target="_blank">https://edgeimpulse.com/blog/elevating-quality-standards-with-ai</a></li></ol>

Revolutionizing Engineering Quality Control: The Transformative Power of Edge AI

Edge AI: A Paradigm Shift in Quality Control

"Hey, Alexa, play the latest Taylor Swift album.” Smart speakers offer amazing convenience – from playing your favorite tunes to re-ordering toilet paper – with only a simple voice command. But that convenience can come with a steep cost in privacy that many consumers aren’t even aware they’re paying.We’ve all had the uncanny experience of searching for something on the internet and then suddenly ads for that very thing are popping up everywhere we look online. It’s no coincidence, says Umar Iqbal, assistant professor of computer science &amp; engineering in the McKelvey School of Engineering at Washington University in St. Louis.“My collaborators and I uncovered that Amazon uses smart speaker interaction data to infer user interests and then uses those interests to target personalized ads to the user,” Iqbal said. “That’s something that Amazon was not upfront about before our research.”The team presented its work Oct. 26 at the ACM Internet Measurement Conference in Montreal, where they received the best paper award. They aim to provide visibility into what information is captured by smart speakers, how it is shared with other parties, and how it is used by such parties, allowing consumers to better understand the privacy risks of these devices and the impact of data sharing on people's online experiences.To crack open the black box around smart devices and the data they capture, the research team built an auditing framework to measure the collection, usage and sharing of Amazon Echo interaction data. First, they created several personas with interests in specific categories and one control persona. Each persona interacted with a different Echo device, then the researchers measured data collection by intercepting network traffic and inferred data usage by observing ads targeted to each persona on the web and on Echo devices.The team reported that as many as 41 advertisers sync or share their cookies – which are typically linked to personal information – with Amazon, and then those advertisers further sync their cookies with 247 other third parties, including advertising services.They also found that Amazon did not clearly disclose that users’ smart speaker interactions are used for profiling them for the purposes of ad targeting. Specifically, Amazon's general privacy policy and Alexa-specific privacy disclosures did not mention that smart speaker interactions are used for ad targeting. However, after their work’s preprint was released and Amazon was made aware, Amazon updated the Alexa Privacy Hub and Alexa Device FAQs to include that Alexa Echo interaction data is used for ad targeting.“Unfortunately, surveillance is the business model of the internet,” Iqbal said. “The issues we identified in our study seem to be part of the design of the smart speaker ecosystem, and the purpose of our study is to bring public transparency. In fact, after our work's preprint was released, Amazon updated its disclosure to include that it uses smart speaker interaction data for ad targeting.”&nbsp;“Consumer protection government agencies, such as the Federal Trade Commission in the U.S. and the European Consumer Organization in the EU have also shown significant interest in our findings,” Iqbal added.Whether interventions by lawmakers or consumer-protection agencies, including recent lawsuits against Amazon by the FTC and consumers themselves, will be successful remains to be seen. Regardless, Iqbal says it’s important for consumers to be aware of just how much data they’re giving away when they invite smart devices into their homes and how that information might be used.<hr>Iqbal U, Bahrami PN, Trimananda R, Cui H, Gamero-Garrido A, Dubois D, Choffnes D, Markopoulou A, Roesner F, and Shafiq Z. Tracking, profiling, and ad targeting in the Amazon smart speaker ecosystem. ACM Internet Measurement Conference (IMC), Oct. 24-26, 2023.&nbsp;<a href="https://umariqbal.com/papers/alexa-echos-imc2023.pdf" target="_blank" data-lf-fd-inspected-kn9eq4roawkarlvp="true">https://umariqbal.com/papers/alexa-echos-imc2023.pdf</a>This work is supported in part by the National Science Foundation (CNS-1956393, CNS-1955227, CNS-2103439, CNS-2114230, CNS-1909020), the Computing Research Association for the CIFellows 2021 Project (CNS-2127309), the Northeastern University Future Faculty Fellowship (2021), and the Consumer Reports Digital Lab.

The Amazon Echo smart speaker and Alexa assistant offer convenience in exchange for your data. Umar Iqbal is bringing transparency to how Amazon uses smart speaker interactions for targeted advertising. (Photo by Jonathan Borba on Unsplash)

Umar Iqbal and collaborators developed a framework to measure data collection, sharing and use by smart speaker platforms

Your smart speaker data is used in ways that you might not expect

How neuromorphic computing and BrainChip's Akida solution can benefit AI training


Navigating the Challenges in AI Training

In this episode, we delve into the ever-evolving world of hybrid AI and generative AI models.

Podcast: The Prius of Artificial Intelligence: Hybrid AI Models

For those eager to grasp the intricacies of AI and neuromorphic computing BrainChip's podcast series stands out as a strong source of knowledge. In their 28th episode titled "This Is Our Mission," BrainChip's Rob Telson orchestrates a riveting conversation with Tenstorrent's COO, Keith Witek, and BrainChip's CMO, Nandan Nayampally. This episode provides a treasure trove of insights, making it a must-listen for engineers working in the industry or warning to know more about the cutting edge of computing.<h2 dir="ltr">About the Guests</h2>Rob Telson, the Vice President of Ecosystem and Partnerships at BrainChip, is the dynamic force behind the podcast series. With a keen eye for curating meaningful discussions, Telson ensures that each episode is both enlightening and engaging. His role at BrainChip involves fostering partnerships and building a robust ecosystem, making him the perfect host to bridge the gap between technical intricacies and their real-world implications.&nbsp;Keith Witek, the COO of Tenstorrent, boasts an impressive resume. With degrees spanning Business, Computing, Electrical Engineering, and Law, Witek has left his mark at tech giants like Google and Tesla. His expertise in strategic alliances, especially in consumer electronics, sets the stage for a profound discussion.Nandan Nayampally, BrainChip's CMO, brings to the table a rich history in the semiconductor domain. With stints at AMD, Denali Software, and even Amazon's Alexa, Nayampally's insights into computing trends are invaluable.<h2 dir="ltr">Podcast Key Discussion Points</h2>AI's Staying Power: The realm of technology is no stranger to fleeting trends, but AI is not one of them. As discussed in the podcast, AI has firmly established itself as a transformative force, with its applications and implications reaching far and wide. The consensus between the experts is clear: AI's influence in shaping the future is undeniable, and its role in various sectors is only set to grow.Real-world AI Impacts: The podcast delves into tangible ways AI is making a difference in our lives. From the significant reduction in car-related fatalities due to AI-driven safety features to the potential of personalized healthcare solutions tailored to individual needs, AI's footprint in real-world scenarios is expanding rapidly.Challenges in AI Scalability: Despite its vast potential, AI faces its set of challenges. The podcast highlights issues like the massive influx of data that systems need to process and the impending slowdown of Moore’s Law. These challenges pose questions about the scalability and efficiency of current AI models.Innovative Solutions:&nbsp;The conversation takes an optimistic turn when discussing the solutions. Industry leaders, including BrainChip and Tenstorrent, are at the forefront of addressing these challenges. Their innovative approaches and technologies promise to overcome existing barriers, paving the way for a more AI-integrated future.Promising Tech Deployment Models: The podcast also touches upon the future of technology deployment. The concept of chiplets, for instance, offers a glimpse into the potential shifts in how we might approach hardware design and integration in the coming years, ensuring more efficient and scalable AI implementations.<h2 dir="ltr">Closing Thoughts</h2>This podcast episode is a great resource for anyone interested in the future of AI, regardless of their background or level of knowledge. It promises to offer insights into real-world applications, challenges, and solutions that are shaping the evolution of AI. As the world stands at the brink of an AI revolution, it becomes increasingly important to understand its nuances and potential implications.<a href="https://www.wevolver.com/profile/brainchip" target="_blank" rel="noopener noreferrer">Read more about BrainChip on Wevolver. </a>

artificial intelligence

Latest Posts