Self-Taught Learning to Deep Networks

From Ufldl

Jump to: navigation, search
(Feature Learning pipeline)
Line 7: Line 7:
training data, this can significantly improve your classifier's performance.
training data, this can significantly improve your classifier's performance.
-
== Feature Learning pipeline ==
 
In self-taught learning, we first trained a sparse autoencoder on the unlabeled data.  Then,  
In self-taught learning, we first trained a sparse autoencoder on the unlabeled data.  Then,  
Line 39: Line 38:
as part of the sparse autoencoder training process.  The second layer
as part of the sparse autoencoder training process.  The second layer
of weights <math>\textstyle W^{(2)}</math> mapping from the activations <math>\textstyle a</math> to the output <math>\textstyle y</math> was
of weights <math>\textstyle W^{(2)}</math> mapping from the activations <math>\textstyle a</math> to the output <math>\textstyle y</math> was
-
trained using logistic regression (or softmax regression).
+
trained using logistic regression (or softmax regression).
== Fine-tuning ==  
== Fine-tuning ==  

Revision as of 05:54, 13 May 2011

Personal tools