28 October 2015
We recently open-sourced a new neural networks library called Brainstorm, developed over the past year at the Swiss AI Lab IDSIA by PhD students Klaus Greff and Rupesh Srivastava.
Brainstorm is designed to make neural networks fast, flexible and fun. Lessons learned from earlier open source projects led to new design elements compatible with multiple platforms and computing backends.
Brainstorm already has a robust base feature set, including support for recurrent neural networks (RNNs) such as LSTM, Clockwork, 2D Convolution/Pooling and Highway layers on CPU/GPU. All data is considered sequential, and RNNs are first-class citizens.
The release of Brainstorm was very well received by the open source community. On Github, it became the top trending Python project, and was in the top 3 among all projects within a couple of days. We plan to continue to improve Brainstorm with the help of the community.