0

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:

enter image description here

enter image description here

Why this is happening? Where I am going wrong?

Link to code and data files: https://drive.google.com/open?id=0B02Uz-muAJWWVktyaDFOekU5Ulk

Sayantan Ghosh
  • 998
  • 2
  • 9
  • 29
  • 1
    If I am not mistaken, this RBM/DBN implementation only works on binary inputs. If your input is not binary, you need some extension, e.g. Gaussian-Bernoulli RBM. – hbaderts Dec 10 '16 at 17:17
  • Can you give me a link which has python implementation of Gaussian Bernouli RBM? – Sayantan Ghosh Dec 11 '16 at 18:08

0 Answers0