Building the AI City: Edge-to-Cloud AI Inference for Smart Cities
summary
Claims that neural-network compute demand rises 10,000x in seven years and that video AI scales to about one billion cameras drive a practical stack: training on DGX GPUs, optimizing with CUDA/TensorRT, packaging with DeepStream and deploying on EGX servers. Examples include Verizon retrofitting streetlights for Vision Zero and an air-traffic-control partner automating tower tasks; an ecosystem of 200+ app partners and hospital work via Clara Guardian show deployed, production-grade systems that meet real-time, edge-to-cloud inference needs.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 0:40Company Overview
- 2:22Problem Space
- 5:42Compute Intensity
- 6:29Verizon
- 9:02Neural Networks
- 10:14Metropolis Platform
- 14:51Metropolis Platform Summary
- 16:17Ecosystem Partners
- 18:41Smart Public Space
- 19:37Smart Healthcare
- 20:12Conclusion
- 20:57Learn more
related talks
06mAI in production: The droids you’re looking for
40mFueling the AI Revolution with Gaming
30mLong Term Impact of Artificial Intelligence
22mExtending European Strength with Embedded AI
02mAI Tech's Smart City solution
48mThe Power of Edge AI: Revolutionizing Future of Real-Time, Autonomous Processing
06mAI Inference at the Edge: Beyond the Hype
26mAI will drive the industrial IoT to the cloud