Pete Warden — Practical Applications of TinyML

Pete is the Technical Lead of the TensorFlow Micro team, which works on deep learning for mobile and embedded devices.Lukas and Pete talk about hacking a Raspberry Pi to run AlexNet, the power and size constraints of embedded devices, and techniques to reduce model size. Pete also explains real world applications of TensorFlow Lite Micro and shares what it's been like to work on TensorFlow from the beginning.The complete show notes (transcript and links) can be found here: http://wandb.me/gd-pete-warden---Connect with Pete:📍 Twitter: https://twitter.com/petewarden📍 Website: https://petewarden.com/---Timestamps: 0:00 Intro1:23 Hacking a Raspberry Pi to run neural nets13:50 Model and hardware architectures18:56 Training a magic wand21:47 Raspberry Pi vs Arduino27:51 Reducing model size33:29 Training on the edge39:47 What it's like to work on TensorFlow47:45 Improving datasets and model deployment53:05 Outro---Subscribe and listen to our podcast today!👉 Apple Podcasts: http://wandb.me/apple-podcasts​​👉 Google Podcasts: http://wandb.me/google-podcasts​👉 Spotify: http://wandb.me/spotify​

Om Podcasten

Gradient Dissent is a machine learning podcast from Weights & Biases with hosts Lukas Biewald, Lavanya Shukla and Caryn Marooney. It takes you behind-the-scenes to learn how industry leaders are putting deep learning models in production at NVIDIA, Meta, Google, Lyft, OpenAI, and more.