deepthought is a library for decoding brain activity from electroencephalography (EEG) recordings by using deep learning techniques. It is written in python (2.7) and builds upon Pylearn2 and Theano.
The library is still very young and under active development. If you have any questions or are interested in collaborating, please contact Sebastian Stober <sstober at two dot ca>.
deepthought is released under the 3-claused BSD license, so it may be used for commercial purposes. The license does not require anyone to cite deepthought, but if you use deepthought in published research work, you are encouraged to cite this article:
Sebastian Stober; Daniel J. Cameron & Jessica A. Grahn. Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings. In: Proceedings of Neural Information Processing Systems (NIPS'14), 2014.
Further related research article with linked PDFs and bibtex can be found in my publications list.