Visualizing a Trained Autoencoder

From Ufldl

Jump to: navigation, search
Line 51: Line 51:
<sup>1</sup> ''The learned features were obtained by training on '''whitened''' natural images.  Whitening is a preprocessing step which removes redundancy in the input, by causing adjacent pixels to become less correlated.''
<sup>1</sup> ''The learned features were obtained by training on '''whitened''' natural images.  Whitening is a preprocessing step which removes redundancy in the input, by causing adjacent pixels to become less correlated.''
 +
 +
 +
{{Sparse_Autoencoder}}

Revision as of 10:50, 26 May 2011

Personal tools