EDGE AI FOUNDATION Courses

Visual Language Models for Edge AI 2.0 - Multi-image Reasoning and In-context Learning

Explore cutting-edge innovations in visual language models, focusing on VILA's multi-image reasoning capabilities, AWQ quantization, and efficient edge AI deployment strategies.

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

Physics-Aware Auto Tiny Machine Learning for Edge Devices

Explore physics-aware neurosymbolic AI optimization for resource-constrained devices, combining symbolic techniques with machine learning for enhanced edge computing applications.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Building a Music Genre Recognition Application with TinyML on Raspberry Pi Pico

Discover how to build a music genre recognition system on Raspberry Pi Pico using TensorFlow Lite and CMSIS-DSP, from feature extraction to ML model deployment with LSTM neural networks.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

NanoEdge AI Studio - All On-Device Anomaly Detection for Industry 4.0

Discover how NanoEdge AI Studio enables on-device anomaly detection for Industry 4.0, exploring auto-ML algorithms and practical applications in predictive maintenance using STMicroelectronics' solution.

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

Advancing Medical Imaging Analysis with Multi-task and Hardware-Efficient Neural Architecture Search

Discover how neural architecture search optimizes AI models for edge-deployed medical imaging analysis, combining multi-task learning with hardware efficiency for real-time healthcare diagnostics.

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

Tools and Methodologies for Edge-AI Mixed-Signal Inference Accelerators

Discover tools and methodologies for developing neuromorphic mixed-signal edge-AI accelerators, focusing on hardware-aware training, automatic generation, and optimization for efficient deployment.

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

Designing Efficient Neural Architectures and Scaling Strategies for Edge Computing

Explore efficient neural architectures and scaling strategies for edge computing, covering object detection, tracking, and zero-shot audio classification for IoT devices and embedded systems.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Twofold Sparsity: Joint Bit and Network-level Sparse Deep Neural Networks for Energy-efficient RRAM Computing

Explore innovative techniques for compressing deep learning models through joint bit- and network-level sparsity, optimizing energy efficiency in compute-in-memory architectures.

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

Accelerate Baidu PaddlePaddle Edge AI Software Development with Arm Virtual Hardware

Discover how to accelerate edge AI development using Baidu PaddlePaddle and Arm Virtual Hardware for efficient model deployment, testing, and validation across diverse endpoint devices.

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

Target Classification on Edge Using mmWave Radar - A Novel Algorithm and Real-Time Implementation

Delve into mmWave radar target classification using novel algorithms and real-time implementation on TI's IWRL6432, focusing on edge computing solutions for multiple-target detection.

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

On-Device Domain Adaptation for Noise-Robust Keyword Spotting

Discover how domain adaptation techniques improve keyword spotting accuracy by 25% in noisy environments through on-device learning and noise-augmented speech data refinement.

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

Optimized Event-Driven Spiking Neural Network for Low-Power Neuromorphic Platform

Discover how event-driven spiking neural networks can enable low-power neuromorphic systems through modular architectures and local adaptation rules, with practical FPGA implementation insights.

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

Quantization Techniques for Efficient Large Language Model Inference

Discover advanced quantization methods for optimizing large language model performance on edge devices, focusing on reducing computational costs and memory requirements while maintaining efficiency.

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

Towards Efficient Neural Rendering: From NeRF to Real-Time AR/VR Applications

Explore the evolution and optimization of Neural Radiance Fields (NeRF) for AR/VR applications, focusing on computational efficiency improvements and future challenges in achieving photorealistic rendering.

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

Enabling Seamless TinyML Development and Deployment for Edge Devices

Discover how to efficiently develop and deploy TinyML applications using Renesas' scalable MCU/MPU lineup, ecosystem, and development tools for resource-constrained edge devices.

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