I am using this implementation of DBN. http://deeplearning.net/tutorial/code/DBN.py I am using ecg data to train the model which contains 100 float values (in milivolt unit) per row. When I run this implementation the pretraining cost goes on increasing I dont understand why. I am attaching sample input data files and the code of the DBN where I have modified number of input and output units and batchsize. I have modified the 'load_data' code in logistic_sgd.py so I am attaching that file too. Here is the scenario:
Why this is happening? Where I am going wrong?
Link to code and data files: https://drive.google.com/open?id=0B02Uz-muAJWWVktyaDFOekU5Ulk