TinyEngine - Efficient Training and Inference on Microcontrollers - Lecture 17

Explore the TinyEngine library for efficient training and inference on microcontrollers in this lecture from MIT's course on TinyML and Efficient Deep Learning Computing. Dive into techniques for deploying neural networks on resource-constrained devices like mobile and IoT devices. Learn about model compression, pruning, quantization, neural architecture search, and distillation for efficient inference. Discover efficient training methods including gradient compression and on-device transfer learning. Gain insights into application-specific model optimization for videos, point clouds, and NLP. Get hands-on experience implementing deep learning applications on microcontrollers, mobile phones, and quantum machines through an open-ended design project focused on mobile AI. Access lecture slides and additional course information on the efficientml.ai website.

Lecture 17 - TinyEngine - Efficient Training and Inference on Microcontrollers | MIT 6.S965