Skip to content
All tags

#tinyml

2 posts
aiguideReading MIT 6.5940

MIT 6.5940 Lab 3: Finding a Microcontroller Model with a Supernet, Predictors, and Evolutionary Search

Lab 3 of MIT 6.5940 (Fall 2024) hands you an OFA-trained MCUNetV2 super network (more than 10^19 subnets) and the Visual Wake Words dataset. Ten questions, 100 points plus 10 bonus: implement a MACs/peak-memory efficiency predictor and a three-layer MLP accuracy predictor, write random search and evolutionary search, then find a subnet that reaches at least 92.5% accuracy under 250KB and 60M MACs. This guide maps the question structure and what each question trains. It does not include solutions.

#mit-65940#neural-architecture-search#tinyml#ai-course#mit
aiguideReading MIT 6.5940

MIT 6.5940 L10 MCUNet: Running Neural Networks on a Microcontroller with 320kB of SRAM

An MCU has roughly 256–320kB of SRAM and 1MB of Flash, tens of thousands of times less than a phone. Even an int8 MobileNetV2 needs 5x more peak memory than that. Lecture 10 answers with MCUNet: TinyNAS picks a search space before searching for a subnet, and MCUNetV2's patch-based inference cuts MobileNetV2's peak SRAM from 1372kB to 172kB. The lecture closes with tinyML applications in vision, audio, and anomaly detection.

#mit-65940#ai-course#mit#tinyml#edge-ai#on-device-ai