Hardware Podcasts

AI at the Edge – Myth or Reality

EE Times Current · 11 Nov 2022 · 30m

What this episode covers

Renesas Electronics EVP Silas Chitapetti explains how the convergence of AI, IoT, and 5G creates 'intelligent' devices through AIoT, shifting processing from the cloud to the edge. He details Renesas' strategy of embedding AI acceleration in microcontrollers and microprocessors, supported by the acquisition of Reality AI to handle industrial machine learning workloads. Chitapetti highlights specific use cases like predictive maintenance using current sensing, vision-based authentication, and robotic food preparation, noting that these edge AI applications reduce hardware costs and improve response times.

Most relevant to

large enterprises

Topics

Mentioned

Companies
Renesas Electronics Corporation, Silicon Labs, NVIDIA, AMD, SEMI, Reality AI, Cimplicity
Products
RZ Vision platform, ZV family
Also
Silas Chitapetti, TinyML Consortium

Related episodes from other shows

Other shows on the same ground, closest first.

  • Coredump Sessions · 58m

    #004: The Future of Edge AI and What it Means for Device Makers

    Alex Samuelson, CTO and co-founder of Imagimob, joins Memfault founders Francois Baldassari and Chris Coleman to discuss the practical implementation of Edge AI on embedded devices. They highlight how hardware accelerators like the Cortex-M55 and U55 have enabled GPU-like performance on microcontrollers, allowing for real-time inference in applications such as welding quality monitoring and fall detection. The conversation emphasizes that data collection, labeling, and memory constraints are the primary bottlenecks, requiring device makers to build data acquisition firmware early in the development process. Finally, they discuss the shift toward 'AI as a Service' business models, where hardware companies generate recurring revenue by updating models over the device's lifecycle.

    AI & machine learningMicrocontrollers & dev platforms
    8 chapters

  • IoT For All Podcast · 30m

    Foghorn's Ramya Ravichandar | Ensuring Value with Edge AI in IIoT Applications

    Ramya Ravichandar, VP of Products at Foghorn, explains how the company uses edge AI to deliver real-time value in industrial and commercial IoT deployments. She details Foghorn's evolution from edge analytics to machine learning, highlighting use cases like defect detection at Stanley Black & Decker and workplace safety monitoring. Ravichandar argues that 'proof of value' is critical for scaling IoT projects, as edge computing enables low-latency responses and reduces bandwidth constraints compared to cloud-only architectures. She also discusses the complementary relationship between cloud-based model training and edge-based inference, and Foghorn's new 'Lightning' solutions for rapid deployment.

    AI & machine learningConnected products & IoT
    8 chapters

  • IoT For All Podcast · 26m

    Edge Computing Benefits and Considerations | Pratexo's CEO Blaine Mathieu

    Blaine Mathieu, CEO of Pratexo, explains how edge computing unlocks the value of IoT and AI by processing data locally rather than relying solely on the cloud. He details use cases including bird monitoring at European wind farms and predictive maintenance for power transformers, highlighting benefits like latency reduction, privacy, and resilience. Mathieu also discusses distributed and swarm computing architectures that allow edge nodes to collaborate, ensuring high availability and scalability for industrial applications.

    Connected products & IoTAI & machine learning
    7 chapters

  • Over the Air · 24m

    AI at the Edge: Justin Schneck on the Future of Embedded Devices

    Justin Schneck, co-founder and CPO of Peridio, discusses the evolution of AI from cloud to edge, introducing Peridio's upcoming 'Avocado' OS designed to simplify embedded product development. He and host Ryan Prosser of Very explore the spectrum from cloud AI to embedded AI, noting how specialized silicon and miniaturized models are enabling practical applications like Garmin's radar-enabled bike lights. Schneck argues that while cloud AI handles massive compute, the real value lies in robust, self-initializing embedded systems that reduce hardware complexity for developers.

    Embedded firmwareAI & machine learning
    7 chapters

  • IoT For All Podcast · 20m

    What is Edge AI? | Barbara's David Purón | Internet of Things Podcast

    David Purón, CEO and co-founder of Barbara, explains that Edge AI combines edge computing with artificial intelligence to process data close to IoT devices, driven by the proliferation of 13 billion IoT devices, democratized AI tools, and powerful edge hardware like Jetson and Raspberry Pi. He details how industrial companies use Edge AI for use cases such as optimizing chemical usage in water treatment and detecting fraud in electric utilities, while noting that fragmentation of protocols and OT/IT cultural integration remain significant challenges. Purón positions Barbara’s platform at the 'far edge' to address cybersecurity and interoperability issues in unattended industrial environments, advocating for standards like OPC UA and MQTT to scale these solutions across enterprise infrastructure.

    AI & machine learningConnected products & IoT
    7 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by EE Times Current. The episode itself belongs to its publisher.