Rank: 109 based on 507 downloads (last 30 days) and 1 file submitted
photo

Rasmus Berg Palm

E-mail

Personal Profile:
Professional Interests:

 

Watch this Author's files

 

Files Posted by Rasmus
Updated   File Tags Downloads
(last 30 days)
Comments Rating
12 May 2014 Screenshot Deep Learning Toolbox Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets and more. With examples. Author: Rasmus Berg Palm machine learning, deep learning, autoencoder, neural net, convolutional neural ..., deep belief network 507 15
  • 4.52381
4.5 | 21 ratings
Comments and Ratings on Rasmus' Files View all
Updated File Comment by Comments Rating
13 Aug 2014 Deep Learning Toolbox Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets and more. With examples. Author: Rasmus Berg Palm Umer

29 Jul 2014 Deep Learning Toolbox Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets and more. With examples. Author: Rasmus Berg Palm El-Gaaly, Tarek

I just started using this code and was puzzled by the following (plz excuse me for my newbie questions):

How come the errors on MNIST in the examples are less than state of the art? I get ~0.07 error on the 2-layer DBN-NN in the example. State-of-the-art, as far as I am aware, is higher than this.

Also when visualizing the dbn.rbm{2}.W' layer I see pretty much garbage. There is no structure to the weights like dbn.rbm{1}.W'. What has to be done to enable higher level structure learning.

20 Jul 2014 Deep Learning Toolbox Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets and more. With examples. Author: Rasmus Berg Palm Shen, Jane

How to download this valuable toolbox here... can only from GitHub?

18 Jul 2014 Deep Learning Toolbox Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets and more. With examples. Author: Rasmus Berg Palm BO

nntest.m has an error: it will give all 1s for expected, rather than the column index for each row of y.

function [er, bad] = nntest(nn, x, y)
labels = nnpredict(nn, x);
[I,J]=find(y'==1);
expected = I;
bad = find(labels ~= expected);
er = length(bad) / size(x, 1);
end

17 Jul 2014 Deep Learning Toolbox Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets and more. With examples. Author: Rasmus Berg Palm Ferguson, Bruce

It does not run under version R2014a. All tests crash.

Contact us