search

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
3.8k stars 2.28k forks source link

Computing reconstruction error for every test instance in SAE? #141

Open shehrozskhan opened 9 years ago

shehrozskhan commented 9 years ago

After training SAE using the example provided, I want to compute the reconstruction error for every testing (or training) instance. That is, how can i compute MSE between the output layer and input layer? Is there a way to do it easily? Any help will be greatly appreciated.

regards Shehroz

Tgaaly commented 9 years ago

use nnff(.) and return the error variable nn.e(end) for the test instances.