Top AI and ML announcements
summary
Round-up lists concrete releases and guidance: Coral Dev Board Micro ships as a microcontroller with an Edge TPU and the Coral catalog adds about 40 pretrained models for embedded use; TensorFlow Lite adds quantization, debugging and GPU delegation updates; Keras introduces preprocessing layers with precomputation to cut idle time; guidance covers model and data parallelism for large-model training; an open-source MLOps stack highlights TFX-Addons and a selfie depth estimation model brings 3D effects to the browser.
AI-written summary · about
chapters (5)
- 0:00Start
- 1:22Responsible AI Review Processes
- 1:32Celebrity Recognition API
- 3:40Model Parallelism Approaches
- 4:36Keras Preprocessing
related talks
13mCoral: Expanding the edge AI landscape
45mIntroducing Google Coral: Building On-Device AI
50mML and AI at the edge with Google Coral, EdgeTPU and Cloud Platform
55mEdgeAI - AI in the Palm of Your Hand
47mProduction ready EdgeAI with Eclipse ioFog and Google Coral
12mKeynote: What's New in AI
01h 01mML and the IoT: Living on the Edge
33mWhat's new in Machine Learning
