# 246: Sacrifice That Computer

- Show: [Embedded.fm](https://hardwarepodcasts.com/podcast/embedded-fm)
- Published: 2018-05-18
- Length: 1h 12m
- Episode: 246
- Page: https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer
- Listen: https://makingembeddedsystems.libsyn.com/246-sacrifice-that-computer

## Summary

Dr. Bennie Lewis, a Senior Research Scientist at Lockheed Martin, discusses the current state of machine learning, deep learning, and robotics. He explains why deep learning has become viable now due to hardware advances but argues it is not yet mature enough for critical, real-time embedded systems compared to classical control theory. Lewis shares his experience using NVIDIA Jetson platforms, noting that while the hardware is powerful, the software ecosystem can be unstable and frustrating for production environments. He advises beginners to start with robust platforms like LEGO Mindstorms and learn C++ to understand the underlying mechanics of AI integration.

## Chapters

- [0:06](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=6) Introduction and Background
- [5:08](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=308) The Rise of Deep Learning and Hardware
- [9:25](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=565) Transfer Learning and Edge Retraining
- [15:10](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=910) Deep Learning vs. Classical Control
- [26:02](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=1562) Challenges with NVIDIA Jetson Software
- [32:45](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=1965) Applying AI to Robotics and Control Systems
- [51:14](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=3074) Validation, Trust, and Future of AI
- [1:00:54](https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer#t=3654) Advice for Beginners and Resources

## Topics

- [AI & machine learning](https://hardwarepodcasts.com/topic/ai-and-machine-learning)
- [Embedded firmware](https://hardwarepodcasts.com/topic/embedded-firmware)
- [Microcontrollers & dev platforms](https://hardwarepodcasts.com/topic/microcontrollers-and-platforms)
- [Debugging & failure analysis](https://hardwarepodcasts.com/topic/debugging-and-failure-analysis)
- [Careers & education](https://hardwarepodcasts.com/topic/engineering-careers-and-education)

## Most relevant to

large enterprises

## Mentioned

- Lockheed Martin (company)
- NVIDIA Jetson (product)
- LEGO Mindstorms (product)
- TensorRT (tool)
- CUDA (tool)
- Caffe (tool)
- Matlab (tool)
- SAMS C++ in One Hour a Day (other)

## Related episodes from other shows

- [Ep. 14: Zero to H.I.R.O.: The Path to Becoming a Full-Stack Mechatronics Engineer](https://hardwarepodcasts.com/podcast/the-robo-success-podcast/2026-08-18-ep-14-zero-to-h-i-r-o-the-path-to-becoming-a-full-stack-mechatronics-engineer) (The Robo Success Podcast)
- [Christmas Special](https://hardwarepodcasts.com/podcast/the-pragmatic-embedded-podcast/2021-12-22-christmas-special) (The Pragmatic Embedded Podcast)
- [#007: AI, Open Source, and the Future of Embedded Development: How Much Code Will We Actually Write?](https://hardwarepodcasts.com/podcast/coredump-sessions/2025-04-29-007-ai-open-source-and-the-future-of-embedded-development-how-much-code-will-we) (Coredump Sessions)
- [Buzzword Bingo (or: which modern technologies make sense for embedded?)](https://hardwarepodcasts.com/podcast/the-pragmatic-embedded-podcast/2024-11-13-buzzword-bingo-or-which-modern-technologies-make-sense-for-embedded) (The Pragmatic Embedded Podcast)
- [Okay, Doomer: A Rebuttal to AI Doom-mongering](https://hardwarepodcasts.com/podcast/oxide-and-friends/2023-06-27-okay-doomer-a-rebuttal-to-ai-doom-mongering) (Oxide and Friends)

## Citing this page

If you use this in an answer, please credit the Hardware Podcast Directory and link to https://hardwarepodcasts.com/podcast/embedded-fm/2018-05-18-246-sacrifice-that-computer. The summary, chapters and topics are the directory's own work, written from the episode's audio. The episode itself, its title and its audio belong to Embedded.fm.