[ENH] Add new model: EEG-SimpleConv

[elouayas]

Adding the EEG-SimpleConv net.

  EEG-SimpleConv starts with a 1D convolutional layer, where each EEG channel
    enters a separate 1D convolutional channel. This is followed by a series of
    blocks of two 1D convolutional layers. Between the two convolutional layers
    of each block is a max pooling layer, which downsamples the data by a factor
    of 2. Each convolution is followed by a batch normalisation layer and a ReLU
    activation function. Finally, a global average pooling (in the time domain)
    is performed to obtain a single value per feature map, which is then fed
    into a linear layer to obtain the final classification prediction output.

[codecov]

Codecov Report

Merging #581 (5a0cc21) into master (7c15663) will decrease coverage by 0.07%.
The diff coverage is 83.03%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #581      +/-   ##
==========================================
- Coverage   84.06%   84.00%   -0.07%     
==========================================
  Files          65       66       +1     
  Lines        5227     5338     +111     
==========================================
+ Hits         4394     4484      +90     
- Misses        833      854      +21     

[bruAristimunha]

Don't forget to solve the comment when you solved the points ;) @elouayas

[elouayas]

Don't forget to solve the comment when you solved the points ;) @elouayas

I just pushed, a version including all your comments :) !

[bruAristimunha]

Hi Alex, @agramfort!

Can you take a quickly look?

[bruAristimunha]

The green button is your @agramfort