Kaggle: seizure prediction MATLAB solution -- auto encoder approach

Starter code for completing the Kaggle seizure prediction competition with MATLAB

This is a MATLAB solution to the Melbourne University AES/MathWorks/NIH Seizure Prediction (https://www.kaggle.com/c/melbourne-university-seizure-prediction).
It is built upon using autoencoders and neural nets from the Neural Network Toolbox.

The zip file contains:
1. autoencoder_train.m,
a script that constructs a deep network using autoencoders as explained in the example here: http://www.mathworks.com/help/nnet/ug/construct-deep-network-using-autoencoders.html. After constructing the deep or stacked network, the deep network is adapted with more training data.

2. autoencoder_test.m,
a script that loads the neural net constructed from the training data, and make predictions of validation and test data.