What happens when we redesign computing hardware to work more like the human brain? The results are transformative for edge AI.

Sumit Kumar from Inatera takes us inside the world of neuromorphic computing – a revolutionary approach that's bringing brain-like intelligence directly to sensors. Born from research at Delft University of Technology, Inatera is tackling one of the most significant challenges in modern technology: how to perform complex AI tasks on battery-powered devices without draining power.

The key lies in spiking neural networks that are fundamentally different from conventional AI approaches. These event-driven networks operate with computational dynamics that mimic brain function, resulting in models 100 times smaller than traditional AI while consuming just a fraction of the power. For applications like video doorbells, acoustic scene classification, and wearable healthcare, this means continuous monitoring with millisecond latency at just a few milliwatts – outperforming traditional microcontrollers by at least 10x.

Beyond current applications, neuromorphic computing opens entirely new possibilities. The technology excels not just with conventional vision but with radar sensors and other modalities, particularly in privacy-sensitive situations. Robotics represents another frontier, where neuromorphic systems can enhance environmental perception, process complex sensor fusion, and enable low-latency control. Through academic partnerships and industry collaboration via the Edge AI Foundation, Inatera is helping build the ecosystem that will make neuromorphic computing as ubiquitous as neural networks are today. The future of edge AI may indeed be neuromorphic.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

Smart cities face an impossible challenge - monitoring countless security cameras 24/7 with human operators alone. Edge Matrix is solving this problem with innovative AI technology that transforms how urban environments approach security and monitoring.

Founded in 2019 as a Cloudian spin-off, Edge Matrix has developed sophisticated video AI solutions designed specifically for smart city applications. Their systems can continuously monitor multiple camera feeds, instantly detect anomalies, and alert security personnel when issues arise. What makes their approach unique is the comprehensive nature of their offering - they don't just provide software, but build the rugged hardware needed for outdoor deployment in challenging environments like roadways and public spaces.

The team at Edge Matrix has engineered remarkably resilient systems built around NVIDIA's Jetson platform, incorporating features like supercapacitor backups and secondary control systems that can perform complete power cycles remotely when needed. This ensures their equipment maintains continuous operation without manual intervention. Their newest product, Edge AI Station, bundles ready-made AI applications for common use cases like traffic analysis, people counting, and fire detection, making advanced AI monitoring accessible to organizations without extensive technical resources.

Edge Matrix represents the future of urban security - intelligent, always-vigilant systems that transform ordinary cameras into powerful monitoring tools. As cities continue growing smarter, solutions like these will become essential infrastructure for maintaining safety and security at scale. Want to see how AI is revolutionizing urban monitoring? Visit edgematrix.com to learn more about their innovative approach to smart city technology.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

The quest to create artificial intelligence as efficient as the human brain is one of computing's most fascinating challenges. While today's AI systems consume megawatts of power in massive data centers, your brain accomplishes far more complex tasks on roughly 20 watts—about the same as a dim light bulb. This efficiency gap is what FemtoSense is determined to close.

In this illuminating conversation with Sam from FemtoSense, we dive into the journey of this Stanford spin-off that's revolutionizing edge AI with neuromorphic-inspired computing. The company's very name speaks to their mission—"femto" references the femtojoule, the incredibly tiny amount of energy required for a single neuron in your brain to communicate with another. Their goal? Create AI systems that approach this remarkable biological efficiency.

What makes FemtoSense's approach unique is how they've evolved from pure academic research to commercial viability. Rather than pursuing neuromorphic computing in its purest form, they've distilled its key efficiency principles—sparse computing and spatial locality—into manufacturable, reliable systems. This pragmatic approach is already bearing fruit in consumer wearables like AI-powered hearing aids that maintain 24-hour battery life while delivering sophisticated audio processing, and in smart home devices that offer on-device intelligence without cloud dependence. For battery-powered devices, their technology extends runtime dramatically; for plugged-in devices, it slashes costs by reducing silicon footprint.

As Sam puts it, "Efficiency is the new currency." The principles that make FemtoSense's technology possible aren't tied to any specific market or modality—they represent fundamental improvements in how computing can be done. With global operations spanning the US, Asia, and Europe, and active participation in industry groups like the Edge AI Foundation, FemtoSense isn't just building more efficient chips; they're helping shape a future where AI can be everywhere without consuming the planet's resources.

Curious about the future of efficient AI? Join us at upcoming Edge AI Foundation events and discover how companies like FemtoSense are making AI that's not just smarter, but fundamentally more sustainable.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

What if everything we assumed about AI and data was wrong? In a world obsessed with collecting more and more sensor data, LightScline has discovered something remarkable: we might only need 10% of it.

Drawing inspiration from the human brain's selective attention mechanism, LightScline co-founders Ankur and Ayush Goel have developed an approach that trains AI models to identify only the most information-rich portions of sensor data streams. The results are staggering—models requiring 400x fewer computational operations while maintaining state-of-the-art accuracy across multiple domains.

This revolutionary approach solves two critical problems facing organizations swimming in sensor data: spiraling infrastructure costs (cloud computing, storage, bandwidth) and mounting human capital expenses, where each additional hour of collected data traditionally requires 40+ hours of analysis. By focusing only on what matters, LightSkline's technology dramatically reduces both.

The real-world impact is already evident. A Fortune 150 company monitoring high-value industrial equipment achieved exceptional accuracy using just 10% of their raw data. Another major software provider saw 381x fewer computational operations and 85x faster training times. Perhaps most impressive is the technology's ability to run on tiny edge devices with as little as 264KB of RAM—enabling applications previously considered impossible on resource-constrained hardware.

This efficiency breakthrough isn't just incremental—it's transformative. It allows entirely new applications in wearables, industrial monitoring, and distributed fiber optic sensing (which can generate terabytes of daily data from monitoring kilometers of fiber cable). By bringing both training and inference to the edge, LightSkline is redefining what's possible in physical intelligence.

Want to push more intelligence to the edge while dramatically reducing your computational footprint? Discover how LightSkline's approach could transform your sensing applications and unlock entirely new possibilities in edge AI.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

From cloud dependency to edge autonomy – we explore the frontier of intelligent edge computing with TinkerBlocks co-founder Anoop.

Imagine a world where your machines don't need to phone home to make decisions. That's the vision driving TinkerBlox, a startup founded by former Bosch Digital executives who saw firsthand how IoT implementations were hamstrung by excessive reliance on cloud processing. Their mission: bring intelligence to where the action happens – directly on devices at the edge.

The realization that sparked TinkerBlox came from observing industrial OEMs struggling with cloud-dependent architectures for their "greasy machines." While cloud excels for cloud-native applications, forcing these technologies onto edge devices creates bottlenecks, latency issues, and unnecessary costs. As Anoop explains, "Edge is tomorrow" – not just because of technological evolution, but because practical applications demand localized intelligence that cloud architectures can't efficiently provide.

What makes TinkerBlox unique is their approach to standardization and orchestration for the heterogeneous edge. Drawing inspiration from how cloud providers standardized server operations, they're creating reference architectures that respect edge constraints while enabling interoperability. We hear fascinating examples from automotive systems transitioning to vehicle-to-everything (V2X) communication and defense applications where drone swarms need resilient distributed leadership capabilities when individual units fail. Rather than selling directly to end customers, TinkerBlocks positions itself as the "secret ingredient" enabling system integrators and solution providers to deliver superior edge performance.

Curious about how edge computing might transform your industry? This conversation illuminates how purpose-built edge intelligence can overcome the scalability challenges that have limited IoT adoption. Subscribe to our podcast for more insights on emerging technologies that are reshaping how we interact with the physical world.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

The technological pendulum has swung dramatically over the last two decades. From desktop computing to cloud dominance and now back to the critical importance of edge devices, we're witnessing a renaissance in embedded systems. But this time, they're getting smart.

Rajesh, founder of embedUR, takes us on a journey through this evolution, explaining how his company transformed from connectivity specialists to edge AI innovators. Founded in 2004 to accelerate embedded product development, EmbedUR has positioned itself at the fascinating intersection where traditional embedded engineering meets artificial intelligence. This convergence creates unique challenges – embedded developers understand hardware constraints while AI engineers work in high-level abstractions. Bridging this gap requires careful training, collaboration, and a deep understanding of both worlds.

The real magic happens when we see edge AI in action. Imagine headphones that filter background noise without cloud connectivity, privacy sensors that recognize you without capturing detailed facial images, or coffee machines that remember your preferences just by detecting your presence. These aren't futuristic concepts but working demonstrations EmbedUR has created with partners like STMicro, Synaptics, and NXP. What makes these implementations particularly valuable is their independence from cloud connectivity, enhancing both privacy and security.

Yet commercializing edge AI presents significant hurdles. The journey from a 96% accurate demo to a 99% reliable product involves months of testing across diverse environments and user populations. As Rajesh points out, "Your model is only as good as your dataset," highlighting the critical importance of data curation. Through their Model Nova platform and global partnerships, EmbedUR is helping companies navigate this complex transition from prototype to market-ready product. Ready to explore how intelligence at the edge might transform your industry? The revolution is already underway.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

What happens when you push AI to the absolute edge of networks? Meet Weeteq, a Scottish startup revolutionizing system optimization by bringing intelligence directly into microcontroller control loops.

In this fascinating conversation with Martin from Weeteq, we explore the concept of "Ultra Edge" - technology that operates beyond what we typically consider Edge AI. Unlike conventional approaches that process data at the device level, WeTech's innovation works within the microcontroller itself, detecting and responding to error signals in less than one-tenth of a millisecond. This isn't just incremental improvement; it's challenging fundamental assumptions about what's possible at the lowest levels of our technology stack.

The implications are profound across multiple industries. For industrial automation, WeTech's technology optimizes motor performance without requiring expensive hardware replacements. In electric vehicles, it extends range by reducing energy consumption and minimizing stress on traction motors. Even safety-critical systems in autonomous vehicles benefit from their comprehensive monitoring capabilities. All this comes from a lightweight implementation that works with existing infrastructure - no ripping out and replacing required.

Martin also shares insights into Scotland's vibrant technology ecosystem, tracing his journey from Honeywell to startup founder and highlighting how universities like Strathclyde are fueling innovation in everything from robotics to renewable energy. It's a reminder that groundbreaking technological advances aren't limited to Silicon Valley or other well-known tech hubs.

Ready to discover how ultra-edge computing might transform your industry? Listen now and glimpse the future of real-time system optimization.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org

The line between cloud and edge AI is blurring, and NXP Semiconductors stands at the forefront of this transformation. In this illuminating conversation, Ali Ors, Head of AI Strategy and Technologies at NXP, unveils how the semiconductor giant is embedding dedicated AI acceleration across their entire product portfolio—from basic microcontrollers to sophisticated application processors.

With nearly a decade in the AI space, NXP has developed a comprehensive approach that doesn't position edge against cloud, but rather sees them as complementary forces. "We're not trying to make AI easy," Trescot explains, "we're trying to make it easier" for developers to harness AI capabilities in resource-constrained environments. This philosophy drives their hardware development and software enablement strategy, allowing customers across automotive, industrial, and IoT sectors to deploy sophisticated AI solutions where they're needed most.

Perhaps most fascinating is NXP's advancement in bringing generative AI to the edge. Their imx9.5 processor now supports Large Language Models and Vision Language Models with up to 8 billion parameters, shifting the primary constraint from computation to memory limitations. This capability is already finding practical applications in conversational interfaces and scene understanding across industries, where hallucination-free, fact-based responses are non-negotiable. With their pending Kinara acquisition and active participation in the Edge AI Foundation, NXP continues to expand their ecosystem and push the boundaries of what's possible at the intelligent edge. Curious about how edge AI could transform your industry? Dive into this episode to discover the silicon that's making it happen.

Send us a text

Support the show

Learn more about the EDGE AI FOUNDATION - edgeaifoundation.org