The Rise and Impact of Edge AI
summary
Edge AI deploys models on cameras, sensors and phones to cut latency, keep sensitive data local, and drop bandwidth and power use; examples shown include manufacturing anomaly detection, drone crop monitoring, smartwatch health monitoring, camera traffic control and autonomous driving prototypes that run on-device. Implementation emphasizes TensorFlow Lite PyTorch Mobile and ONNX Runtime, model optimizations like pruning and quantization and evaluation by latency, throughput, CPU/GPU/memory, power, accuracy/F1 and environmental and security stress tests.
AI-written summary · about
chapters (7)
- 0:00Introduction to Edge AI
- 1:09What is Edge AI
- 2:15Real-world Edge AI use cases
- 3:19Implementing Edge AI solutions
- 4:46Edge AI vs Cloud AI
- 5:48Evaluating Edge AI applications
- 9:21Key evaluation factors
related talks
22mEdge AI Use Cases in IoT — Unlocking Intelligence at the Network Edge
21mUnlocking the potential of low-power embedded devices with Edge AI software
55mEdgeAI - AI in the Palm of Your Hand
48mThe Power of Edge AI: Revolutionizing Future of Real-Time, Autonomous Processing
01mWhy edge AI is becoming the default for devices
36mApplied AI on the edge
06mEdge AI in Practice: Lessons from Producti...
37mDeep Learning Neural Network Acceleration at the Edge