Visualizing a Trained Autoencoder

From Ufldl

Jump to: navigation, search
Line 34: Line 34:
When we do this for a sparse autoencoder (trained with 100 hidden units on
When we do this for a sparse autoencoder (trained with 100 hidden units on
-
10x10 pixel inputs we get the following result:
+
10x10 pixel inputs<sup>1</sup> we get the following result:
[[Image:ExampleSparseAutoencoderWeights.png|thumb|400px|center]]
[[Image:ExampleSparseAutoencoderWeights.png|thumb|400px|center]]
Line 48: Line 48:
domains too.
domains too.
-
''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.''

Revision as of 23:33, 22 April 2011

Personal tools