Stacked Autoencoders

From Ufldl

Jump to: navigation, search
(Overview)
Line 21: Line 21:
</math>
</math>
-
The information of interest is contained within <math>a^{(n)}</math>, which is the activation of the deepest layer of hidden units. This vector gives us a representation of the input in terms of higher-order features. The stacked autoencoder can be used for classification problems by feeding a(1) to a softmax classifier.
+
The information of interest is contained within <math>a^{(n)}</math>, which is the activation of the deepest layer of hidden units. This vector gives us a representation of the input in terms of higher-order features.  
 +
 
 +
The features from the stacked autoencoder can be used for classification problems by feeding <math>a(n)</math> to a softmax classifier.
===Training===
===Training===

Revision as of 00:26, 12 May 2011

Personal tools