search

kyunghyuncho / deepmat

Matlab Code for Restricted/Deep Boltzmann Machines and Autoencoders
http://users.ics.aalto.fi/kcho/
188 stars 95 forks source link

Small typo in mlp.m #2

Closed vktt closed 11 years ago

vktt commented 11 years ago

line 23 is: valid_targest = []; should be: valid_targets = []; It is only an issue if less than 3 parameters are passed to the function (nargin<3)

Also, I have a question:

In default_mlp.m, why are you using binary input and binary outputs?

% data type
M.data.binary = 1;
%M.data.binary = 0;

% output type
M.output.binary = 1;

Thanks, Vikrant.

kyunghyuncho commented 11 years ago
  1. Thanks for pointing it out. It's been now fixed.
  2. default_mlp.m: It's just a default value, and you can change it by simply setting M.data.binary or M.output.binary = 0. In fact, in the case of MLPs, the input type does not really matter at all, but the output type should be set accordingly depending on whether you're aiming to do classification (M.output.binary = 1) or regression (M.output.binary = 0)