tinyML Courses

TinyML Talks - Building TinyML Applications Using Rune

Explore containerization for TinyML apps using Rune and Hammer. Learn to build efficient, portable solutions for healthcare, field ops, and telecom, with a focus on cough detection in public spaces.

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

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

Explore SRAM-based in-memory computing for energy-efficient AI inference, covering bitcell circuits, architectures, and design optimization for improved performance in low-power processors.

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

Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices

Explore hyperdimensional computing optimization for edge devices, reducing model size and energy consumption while maintaining accuracy in lightweight machine learning applications.

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

SWIS: Shared Weight Bit Sparsity for Efficient Neural Network Acceleration

Explore SWIS, a quantization framework for efficient neural network inference acceleration, offering improved performance and storage compression through weight decomposition and scheduling algorithms.

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

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

Explore hls4ml, an open-source workflow for implementing machine learning algorithms on FPGAs and ASICs, enabling real-time processing for scientific applications and accelerating discoveries.

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

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

Explore software runtime for hybrid multicore architecture in TinyML, focusing on efficient resource allocation, minimized processing overhead, and optimized memory transfers for edge AI hardware.

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

How Adaptive AI Solves Big Challenges for tinyML

Explore how Adaptive AI addresses challenges in tinyML, enabling efficient deployment of Edge AI models for smart devices and enterprise solutions.

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

Adaptive Neural Networks for Agile TinyML - Keynote

Explore adaptive neural networks for efficient tinyML, enabling dynamic footprint minimization and runtime flexibility. Learn about throttleable networks, controller training, and hardware acceleration.

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

Market Opportunities for Edge AI

Explore market opportunities for edge ML with industry experts, discussing growth potential, future trends, and promising technologies in industrial applications, smart buildings, and IoT.

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

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

Exploring the journey from tinyML face detection demos to large-scale commercial deployment, addressing real-world challenges and bridging the gap between prototypes and practical applications.

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

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

Explore sparsity exploitation in AI edge applications for faster response times. Learn about NeuronFlow architecture, latency metrics, and real-time AI implementation strategies.

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

tinyML: Impact and Growth of Always-On Devices

Explore the growing impact of tinyML devices in everyday life, from always-on voice in phones to environmental sensing in machines, and learn about the market's rapid expansion and technological requirements.

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

Memory-Efficient, Limb Position-Aware Hand Gesture Recognition Using Hyperdimensional Computing

Memory-efficient hand gesture recognition using hyperdimensional computing and sensor fusion. Improves accuracy by 17.79% while reducing memory footprint, addressing limb position changes for human-machine interfaces and prosthetics.

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

Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support

Innovative smartphone security: Deep Learning for quick impostor detection, preserving user privacy with on-device processing and minimal hardware support.

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

Hardware Aware Training for Efficient Keyword Spotting - tinyML Research Symposium 2021

Explore hardware-aware training for efficient keyword spotting, focusing on Legendre Memory Unit networks to achieve state-of-the-art accuracy and power efficiency on various hardware platforms.

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