Building Machine Learning models with Edge Impulse
summary
Edge Impulse is presented as an end-to-end TinyML platform with 40,000 projects in the community, a web IDE that ingests sensor or audio data via QR-collected uploads, AutoML and a visual and expert TensorFlow modes pipeline. A live demo trains keyword detection from 46 minutes of collected audio, inspects separability in a feature explorer, and reports 96.6% training / 94% test accuracy. Documentation, device getting-started guides and two Coursera courses provide step-by-step follow-ups.
AI-written summary · about
chapters (3)
related talks
15mBuild a custom Edge Machine Learning solution to monitor your shipments conditions with Edge Impulse
38measily create, deploy, and monitor mobile AI models
45mUsing Edge Machine Learning to save power and development time
09mMachine Learning on the Edge
22mEdge AI Use Cases in IoT — Unlocking Intelligence at the Network Edge
55mEdgeAI - AI in the Palm of Your Hand
40mHands-on TinyML Deployment on RISC-V: Building an Optimized Edge AI Pipeline
45mEdge Impulse & Android: Democratizing AI at the Edge