tinyML Courses

Using AI to Design Energy-Efficient AI Accelerators for the Edge

Explore AI-driven co-design of neural networks and hardware accelerators for edge devices, optimizing accuracy and efficiency through simultaneous architecture and hardware space exploration.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Embedded Machine Learning Using Infineon’s ModusToolbox ML

Explore embedded machine learning deployment using Infineon's ModusToolbox ML, focusing on IoT applications and unique features for small embedded platforms. Learn about the development flow and future roadmap.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Acceleration of Deep Learning Inference on Raspberry Pi's VideoCore GPU

Explore techniques for accelerating deep learning inference on Raspberry Pi's VideoCore GPU, including optimized tools, libraries, and compilers for enhanced performance without compromising accuracy.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

System Software for Machine Learning at the Edge - tinyML Asia 2020

Explore system software approaches for optimizing ML on edge devices, focusing on compiler and runtime techniques to maximize hardware potential for mobile and IoT applications.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Amber - A Complete, ML-Based, Anomaly Detection Pipeline for Microcontrollers

Discover a complete ML-based anomaly detection pipeline for microcontrollers, featuring real-time sensor value processing, automatic hyperparameter tuning, and high-speed inference capabilities.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Enabling Neural Network at the Low Power Edge - A Neural Network Compiler

Explore neural network deployment in IoT devices, addressing challenges and optimizing for ultra-low power operation through hardware-software co-optimization and automatic code generation.

• YouTube
• 36 minutes
• Self-Paced
• Free Video

Structured Quantization for Neural Network Language Model Compression

探讨神经网络语言模型的结构化量化压缩技术,展示如何在不损失性能的情况下实现70-100倍的高压缩率,适用于资源受限场景。

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Toward Data-Driven Applications with AIoT Devices

Explore data-driven AIoT applications, model reduction techniques, and meta-learning approaches for enhanced inference accuracy in diverse environments, with real-life examples and future research directions.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Powering Innovation in AI Devices on the Edge with Micro-NPUs - tinyML Asia 2020

Explore Arm's Ethos-U micro-NPUs for efficient AI processing on edge devices, enabling new applications and capabilities in embedded systems through advanced Machine Learning solutions.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

The Road to Innovation for AI Chips in China

Explore China's AI chip innovation landscape, including market growth, startups, academic advancements, and emerging technologies like reconfigurable computing and neuromorphic chips.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Tiny but Powerful: Hardware for High Performance, Low Power Machine Learning

Explore cutting-edge hardware for ultra-low power machine learning at the edge, covering TinyML applications, model optimization, and emerging trends in efficient computing.

• YouTube
• 1 hour
• Self-Paced
• Free Video

How to Build Advanced Hand-Gestures Using Radar and TinyML

Explore advanced hand gesture control using radar and Edge AI for headphones, featuring a case study and development process with Imagimob AI software.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Networks Within Networks - Novel CNN Design Space Exploration for Resource-Limited Devices

Explore novel CNN design for resource-limited devices using "network within network" paradigm. Learn automated method for compressing neural networks while preserving accuracy and meeting size constraints.

• YouTube
• 31 minutes
• Self-Paced
• Free Video

Introduction to Optimization Algorithms to Compress Neural Networks

Explore optimization techniques for compressing neural networks, including pruning and quantization, to enable deployment on resource-constrained devices like smartphones.

• YouTube
• 48 minutes
• Self-Paced
• Free Video

A Technique for Extreme Compression of LSTM Models

Explore extreme LSTM compression using sparse structured additive matrices. Learn doping techniques, co-matrix adaptation, and regularization for state-of-the-art accuracy at high compression factors in NLP applications.

• YouTube
• 53 minutes
• Self-Paced
• Free Video