EEGNET implementation

Part of https://arxiv.org/pdf/1609.03499.pdf that most concerns classification: "As a last experiment we looked at speech recognition with WaveNets on the TIMIT (Garofolo et al., 1993) dataset. For this task we added a mean-pooling layer after the dilation convolutions that aggregated the activations to coarser frames spanning 10 milliseconds (160 x downsampling). The pooling layer was followed by a few non-causal convolutions. We trained WaveNet with two loss terms, one to predict the next sample and one to classify the frame, the model generalized better than with a single loss and achieved 18.8 PER on the test set, which is to our knowledge the best score obtained from a model trained directly on raw audio on TIMIT."

Look into: http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/43290.pdf "Input: This layer extracts 275 ms waveform segments from each of M input microphones. Successive inputs are hopped by 10ms. At the 16kHz sampling rate used in our experiments each segment contains M X 4401 dimensions." ....