How use get final representation of the data after applying a already trained SAE weights?

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

How use get final representation of the data after applying a already trained SAE weights? #96

Open erogol opened 10 years ago

erogol commented 10 years ago

I have a data and like to get its final representation after I forward propagate it through SAE. What is the correct function that I can use in a ease manner?

For instance:

D is data matrix , SAE is the final model that I learned. What function would give the F that is the final representation of D after FF through SAE.

Sorry this is not a issue but I found here to ask this question to a certain owner.

rasmusbergpalm commented 10 years ago

see https://github.com/rasmusbergpalm/DeepLearnToolbox/blob/master/tests/test_example_SAE.m on how to unfold your SAE into a NN. from there on it should be fairly easy