A tensor serves as the central unit of data. Also, a high-level, Keras-inspired API is included for building neural networks.
Planned enhancements for TensorFlow.js include:
- A visualization library to perform quick visualizations of the model and data.
- Performance improvements in the browser.
- WebGL optimization.
- A browser- and Node-specific data API.
- Cloud integration on the Node.js side, including serverless-type integration points.
- Better async support with the libuv asynchronous I/O library.