Rank: 60926 based on 0 downloads (last 30 days) and 0 file submitted
photo

Tarek El-Gaaly

E-mail

Personal Profile:

 

Watch this Author's files

 

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

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.

Contact us