Defining Your AI Eco-System with Advantech
summary
Outlines an Advantech-led industrial AI stack that keeps inference at the edge to avoid cloud latency, cost, and security issues, using Jetson-based edge boxes and x86 SKY-6100/SKY-6000 servers that can host up to 10 Teslas (V100s) for training; middleware relies on CUDA X and DeepStream, ISV partners include BrainCreators (BrainMatter) for pipeline and Neurocat for AI robustness, and deployments run off‑premise, on‑premise or hybrid with Docker/Kubernetes for model delivery and retraining.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 0:31Challenges
- 1:53Advantech Ecosystem
- 5:05Different Models
- 7:38Business Model
- 8:24Outro
related talks
26mBuilding a Cloud Native Edge Platform for Accelerating AI Inference
09mTackling edge computing with Intel's AI Builders program
40mFueling the AI Revolution with Gaming
50mAI acceleration at the edge
06mAI Inference at the Edge: Beyond the Hype
48mThe Power of Edge AI: Revolutionizing Future of Real-Time, Autonomous Processing
22mEdge AI Use Cases in IoT — Unlocking Intelligence at the Network Edge
21mA New Architecture for the Intelligent Edge