Accelerating deep neural networks on the web
A new web standard that allows web apps and frameworks to accelerate deep neural networks with on-device hardware such as GPUs, CPUs, or purpose-built AI accelerators.
Combining the best of both worlds
by taking advantage of performant numerical computation capabilities and the reach of the web
- Low Latency
- In-browser inference enables novel use cases with local media sources.
- Privacy Preserving
- User data stays on-device and preserves user-privacy.
- High Availability
- No reliance on the network after initial asset caching for offline case.
- Low Cost
- Computing on client devices means no server farms needed.
- Take advantage of the native OS services for machine learning
- Get capabilities from the underlying hardware innovations
- Implement consistent, efficient, and reliable AI experiences on the web
- Benefit web applications and frameworks including TensorFlow.js, ONNX.js
Web Machine Learning Working Group Launch