rasmusbergpalm / DeepLearnToolbox

Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
BSD 2-Clause "Simplified" License
3.79k stars 2.28k forks source link

CAE does not pass gradient check. #43

Open reedscot opened 11 years ago

reedscot commented 11 years ago

In caetrain.m, when I uncomment the numerical gradient checking, it does not pass.

rasmusbergpalm commented 11 years ago

What OS/program?

reedscot commented 11 years ago

Red Hat Enterprise Linux Server release 5.9 (Tikanga) Matlab R2013a

On Mon, Jul 1, 2013 at 3:13 AM, Rasmus Berg Palm notifications@github.comwrote:

What OS/program?

— Reply to this email directly or view it on GitHubhttps://github.com/rasmusbergpalm/DeepLearnToolbox/issues/43#issuecomment-20266348 .

rasmusbergpalm commented 11 years ago

conv('valid') in octave has numerical instability. We're working on a workaround

zym1010 commented 10 years ago

I have this problem too, using MATLAB R2013a on Mac OS X 10.9.2