{
  "id": 4607,
  "title": "Cost evaluation in mlp model",
  "url": "/competitions/challenges-in-representation-learning-the-black-box-learning-challenge/discussion/4607",
  "author_name": "José A. Guerrero",
  "post_date": "2013-05-16T11:04:32.960000",
  "votes": 0,
  "comment_count": 0,
  "views": 1007,
  "content": "<div></div>\r\n<div>I'm trying to modify 'cost' in mlp model (pylearn2/models/mlp.py) and before would like simplify it (only for experimenting and personal learning)</div>\r\n<div></div>\r\n<div>I think theano expression:</div>\r\n<div></div>\r\n<div>T.nnet.categorical_crossentropy(T.nnet.softplus(Y_hat),Y).mean(axis=1)</div>\r\n<div></div>\r\n<div>could evaluate directly the cost.&nbsp;</div>\r\n<div></div>\r\n<div>I don't understand the purpose of the lines 648-659 and the use of several other lines in the actual code.</div>\r\n<div></div>\r\n<div>Someone with knowledge in theano - pylearn &nbsp;could tell me something about them?</div>",
  "messages": [
    {
      "id": 24382,
      "postDate": "2013-05-16T11:04:32.960Z",
      "content": "<div></div>\r\n<div>I'm trying to modify 'cost' in mlp model (pylearn2/models/mlp.py) and before would like simplify it (only for experimenting and personal learning)</div>\r\n<div></div>\r\n<div>I think theano expression:</div>\r\n<div></div>\r\n<div>T.nnet.categorical_crossentropy(T.nnet.softplus(Y_hat),Y).mean(axis=1)</div>\r\n<div></div>\r\n<div>could evaluate directly the cost.&nbsp;</div>\r\n<div></div>\r\n<div>I don't understand the purpose of the lines 648-659 and the use of several other lines in the actual code.</div>\r\n<div></div>\r\n<div>Someone with knowledge in theano - pylearn &nbsp;could tell me something about them?</div>"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "24382": ""
  }
}