AI Forum – Pietro Colocca
summary
Pietro Colocca from Intel explains how to optimize AI applications for edge inference, focusing on techniques and tools to improve performance on edge devices. The presentation covers Intel-specific solutions and best practices for deploying and tuning models for low-latency, resource-constrained environments.
AI-written summary · about
chapters (11)
- 0:00Welcome
- 1:22AI use cases at edge
- 2:48Edge vs cloud benefits
- 5:00Intel AI software ecosystem
- 7:04OpenVINO and heterogeneous computing
- 9:12Performance with Intel processors
- 11:40Pre-trained models and computer vision
- 13:25OpenVINO in practice and cloud sandbox
- 14:50Industrial use case demo
- 15:55Summary
- 16:36Q&A
related talks
09mTackling edge computing with Intel's AI Builders program
22mEdge AI Use Cases in IoT — Unlocking Intelligence at the Network Edge
50mAI acceleration at the edge
21mUnlocking the potential of low-power embedded devices with Edge AI software
24mTools & Techniques for a cost optimized Analytics & AI pipeline
06mAI Inference at the Edge: Beyond the Hype
10mThe Rise and Impact of Edge AI
13mAccelerating AI algorithms