EDGE AI FOUNDATION Courses

Minimizing Resource Usage in Microcontrollers for Cost-Effective Solutions

Discover optimization techniques for microcontrollers using Apache TVM and Arm Ethos-U55, focusing on neural network fine-tuning strategies to reduce costs and energy consumption.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Suitability of Forward-Forward and PEPITA Learning to MLCommons-Tiny Benchmarks

Explore forward-only algorithms as alternatives to backpropagation in on-device learning, examining memory efficiency and computational trade-offs for tiny ML devices through MLCommons-Tiny benchmarks.

• YouTube
• 1 hour
• On-Demand
• Free Video

Unsupervised Federated Learning for Edge Computing Applications

Explore federated learning techniques for edge devices, focusing on utilizing unannotated data to build global models while maintaining data privacy and security in IoT applications.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video

Enabling On-Device Learning on STM32 Microcontrollers

Discover how to implement on-device learning for CNN models on STM32 microcontrollers, focusing on personalized Human Activity Recognition and resource optimization for edge computing.

• YouTube
• 1 hour 11 minutes
• On-Demand
• Free Video

Hardware-Aware Neural Architecture Search Algorithm for Ultra-Low-Power Microcontrollers

Discover how hardware-aware neural architecture search enables efficient AI model design for microcontrollers, optimizing performance without requiring powerful GPUs or extensive computing resources.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Biosensing at the Edge of the Cloud - Applications in Clean Water, Food Quality, and Health

Explore cutting-edge biosensor technologies for smart bio-edge applications, covering virus detection, water quality monitoring, food safety, and health tracking through chemical and biological data analysis.

• YouTube
• 1 hour 7 minutes
• On-Demand
• Free Video

Mudra - Reinventing Tiny Interfaces for Ubiquitous Digital Interaction

Explore how Mudra's wearable technology revolutionizes digital interaction through bio-potential sensing and IMU integration, enabling touchless control across multiple devices while maintaining low power consumption.

• YouTube
• 1 hour 6 minutes
• On-Demand
• Free Video

Empowering the Edge - Advancements in AI Hardware and In-Memory Computing Architectures for TinyML

Explore cutting-edge AI hardware architectures and in-memory computing innovations for efficient edge computing, focusing on real-time inference and resource optimization for TinyML applications.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

A TinyML Approach to Deploy Reduced-Order Model of Complex Systems on Microprocessor

Discover how to deploy reduced-order models on microprocessors using TinyML, focusing on compression techniques and real-time applications like battery management in vehicles.

• YouTube
• 1 hour
• On-Demand
• Free Video

From the Cloud to the Edge: Reverse-Engineering and Downsizing a Black Box ML Algorithm for Sleep Stage Prediction

Discover how to reverse-engineer and downsize black box ML algorithms for edge computing, focusing on sleep stage prediction and efficient data collection techniques for embedded systems.

• YouTube
• 24 minutes
• On-Demand
• Free Video

Ultra-Fast Energy-Efficient Neuromorphic Edge Processing for Event-Based and Frame-Based Cameras

Explore cutting-edge neuromorphic processing for event-based cameras, focusing on ColibriUAV and ColibriEYE platforms powered by the Kraken SoC for ultra-efficient UAV perception and eye tracking applications.

• YouTube
• 26 minutes
• On-Demand
• Free Video

Smart and Connected Soft Biomedical Stethoscope and Machine Learning for Continuous Real-Time Disease Detection

Discover how soft wearable stethoscope technology combines with machine learning to enable continuous cardiopulmonary monitoring and automated disease detection with 95% accuracy in clinical settings.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Monostable Multivibrator Networks - Extremely Low Power Inference at the Edge with Timer Neurons

Explore the potential of Monostable Multivibrator Networks for edge computing, focusing on timer-based neural networks and their implementation for low-power inference applications.

• YouTube
• 23 minutes
• On-Demand
• Free Video

Ultra-Low Power Gesture Recognition with pMUT Arrays and Spike-based Beamforming

Explore ultra-low power gesture recognition using pMUT arrays and spike-based beamforming, achieving 86% accuracy through innovative spiking domain processing and neural networks.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Event Sensors for Embedded Edge AI Vision Applications - Design and Implementation

Explore event-based vision sensing technology and its applications in embedded edge AI systems, focusing on Prophesee's innovative sensor design for improved integration and power efficiency.

• YouTube
• 20 minutes
• On-Demand
• Free Video