Hardware Podcasts

190. Here's a Free Tool To Test Your AI

The Next Byte Podcast · 3 Sept 2024 · 17m

What this episode covers

Daniel and Forbode discuss Robuscope, a free online testing tool developed by the Fraunhofer Institute to evaluate the robustness of AI models. They highlight its utility in high-stakes fields like medical diagnostics and autonomous driving, explaining how it provides detailed reports on metrics such as F-score and calibration error without requiring proprietary source code. The hosts also note limitations, such as the requirement for an internet connection, which may hinder adoption in secure environments.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Fraunhofer Institute, Facebook, Amazon, Tesla
Products
ChatGPT
Tools
Robuscope

Related episodes from other shows

Other shows on the same ground, closest first.

  • Global Medical Device Podcast · 24m

    #345: Using AI In MedTech

    Wade Schroeder, Medical Device Guru at Greenlight Guru, discusses the state of AI in MedTech, highlighting that 65% of professionals distrust AI data accuracy due to unknown sources. He explains how Greenlight Guru’s Risk Intelligence tool uses Bayesian statistics and natural language processing to pull data from the FDA’s MAUDE database, helping engineers address the 'cold start' problem in risk management. Schroeder also introduces the 'Digital Guru,' an AI bot trained specifically on FDA regulations to ensure compliance and trust, contrasting it with general models like ChatGPT.

    AI & machine learningQuality & yield
    7 chapters

  • Embedded.fm · 54m

    446: World's Best PB&J

    Hosts Elecia White and Christopher White interview an AI language model, referred to as 'Christopher White' or ChatGPT, discussing its capabilities and limitations in embedded systems and software development. They explore the use of tools like Compiler Explorer (godbolt.org) and Google Colab for coding tasks, and discuss the complexities of using ArduPilot for drone projects. The conversation highlights the distinction between statistical language models and true artificial intelligence, noting issues with hallucination and lack of reasoning.

    AI & machine learningEmbedded firmware
    7 chapters

  • The Robot Report Podcast · 55m

    Open source visualization and debugging for robotics

    Adrian Macneil, co-founder and CEO of Foxglove, discusses the company's open-source visualization and debugging tool for robotics, which spun out from his time at Cruise. He explains how Foxglove Studio addresses the limitations of RViz by offering cross-platform support and handling massive sensor data logs via WebGL and WebAssembly. Macneil also details the company's recent $3.7 million seed funding, its strategy of providing a free open-source core with a commercial data platform for collaboration, and his advice for early-stage hardware founders.

    Debugging & failure analysisStarting a product company
    7 chapters

  • EE Times Current · 40m

    CEO Interview: Flex Logix’ Geoff Tate on AI | Open Source Hits Hardware

    Geoff Tate, CEO of Flex Logix, explains the distinction between AI training and inference, arguing that engineers must benchmark their specific neural network models on target chips rather than relying on generic metrics like TOPS, which he demonstrates can be misleading compared to real-world performance on models like YOLO V3. Industry analyst Kevin Krewell discusses the rise of open technologies in hardware, tracing the evolution from open source software like Linux to open RAN in networking and the growing ecosystem around the open-source RISC-V architecture as an alternative to proprietary instruction sets like ARM and x86.

    AI & machine learningChips, FPGAs & semiconductors
    6 chapters

  • Coredump Sessions · 1h 01m

    #021: Hardware at Software Speed: How BootLoop Is Bringing AI to the Bench for Firmware Teams

    Noah Pasek-Nelson and Chris Markus, co-founders of BootLoop, explain how their AI platform accelerates the firmware lifecycle by combining deep hardware context with automated hardware-in-the-loop testing. They discuss how ingesting schematics and data sheets eliminates hallucinations, allowing the system to generate, flash, and validate code on physical devices like oscilloscopes and logic analyzers. The founders also cover BootLoop's security posture, pricing model, and its 'Sentinel' product for automated field debugging.

    AI & machine learningEmbedded firmware
    7 chapters

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