TinyML for All: Full-stack Optimization for Diverse Edge AI Platforms

This course presents full-stack methods for deploying neural networks on resource-constrained microcontroller units. It covers model compression, neural architecture rebalancing, training-memory reduction, inference optimization, and vision and point-cloud applications.

Syllabus

Intro
TinyML is about Constraints
Everything Together: Real-world Al on Tiny MCUS
Brief History of MCUNets
Opportunity in Fundamental ML Algorithms
New Problem: Imbalanced Memory Distribution of CNNS
Solving the Imbalance with Patch-based Inference
MCUNet-v2 Takeaways
Once-for-All Network
Problem in Training for Tiny Models
NetAug for TinyML
Problem: Training Memory is much larger
TinyTL: Up to 6.5x Memory Saving without Accuracy Loss
Differentiable Augmentation
TinyML for LIDAR & Point Cloud
Full Stack LIDAR & Point Cloud Processing
Takeaways: Coming Back to MCUNets
Fundamental Problems in TinyML
OmniML "Compress" the Model Before Training
OmniML: Enable TinyML for All Vision Tasks
Founding Team