tinyML Courses

Lessons Learned from Building a TinyML-Powered Artificial Nose

Lessons from building an open-source, open-hardware artificial nose that uses TinyML to classify smells on a microcontroller and connect edge AI with IoT.

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

EMEA 2021 Tiny Talks- Image-Based Target Identification on a Tiny RISC-V Multi-Core Application

A technical talk on deploying image-based neural network inference on low-power multicore RISC-V processors using memory tiling and the AutoTiler tool.

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

Bio-inspired Neuromorphic Circuits Architectures for Ultra-Low Power AI

Explore how brain-inspired neuromorphic circuits emulate neurons and synapses for robust, low-latency, ultra-low-power computation at the extreme edge.

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

TinyML Talks - Building TinyML Applications Using Rune

Build TinyML applications with open-source Rune tooling, configuring models and deploying them through a QR-code workflow to Android and iOS phones.

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

TinyML Talks - SRAM Based In-Memory Computing for Energy-Efficient AI Inference

A technical talk on SRAM-based in-memory computing, from analog memory-array circuits and ADCs to accelerator architectures for energy-efficient AI inference.

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

Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices

Shrinking hypervectors for efficient hyperdimensional computing on edge devices while preserving classifier accuracy and robustness.

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

hls4ml: An Open-Source Co-Design Workflow for Scientific Low-Power Machine Learning Devices

Explore hls4ml’s open-source workflow for translating machine-learning models into low-power FPGA and ASIC implementations for real-time scientific devices.

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

TinyML Summit 2021 Tiny Talks - TinyML Software Runtime for Hybrid Multicore Architecture

How TinyML runtimes schedule neural-network workloads across heterogeneous cores while controlling memory, power, and data movement.

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

How Adaptive AI Solves Big Challenges for tinyML

Explore how Adaptive AI addresses enterprise edge challenges and helps build and deploy tinyML models for smart devices.

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

Adaptive Neural Networks for Agile TinyML - Keynote

Adaptive neural networks dynamically reduce memory and compute demands for agile TinyML inference.

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

TinyML Journey: From Face Detection Demo to Real-Life Commercial Deployment

A TinyML case study on turning a face-detection demo into robust, real-world commercial deployment on low-cost microcontrollers.

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

Leveraging Sparsity for Fast Response Times in Edge AI - tinyML Summit 2021

Explore how sparsity and the NeuronFlow multicore architecture enable low-latency, real-time AI applications at the edge.

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

Many Shades of Acceleration - An Open TinyML Platform Perspective

Explores how open RISC-V platforms balance specialized hardware acceleration, flexibility, and sub-milliwatt power for TinyML at the extreme edge.

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

Advanced Network Quantization and Compression Using AIMET - tinyML Summit 2021

Learn advanced neural network quantization and compression techniques with Qualcomm’s AI Model Efficiency Toolkit for efficient edge-device AI.

• YouTube
• 1 hour 34 minutes
• Self-Paced
• Free Video

Build Industrial-Grade TinyML Applications with Edge Impulse - Tutorial

Build an industrial tinyML application end to end, from sensor data collection and model training through quantization, anomaly detection, and deployment on an MCU.

• YouTube
• 1 hour 37 minutes
• Self-Paced
• Free Video