Sparse Coding: Autoencoder Interpretation

From Ufldl

Jump to: navigation, search
Line 47: Line 47:
(where <math>\sqrt{s^2 + \epsilon}</math> is shorthand for <math>\sum_k{\sqrt{s_k^2 + \epsilon}}</math>)
(where <math>\sqrt{s^2 + \epsilon}</math> is shorthand for <math>\sum_k{\sqrt{s_k^2 + \epsilon}}</math>)
-
Optimizing for this objective function (using the iterative method of optimizing for <math>A</math>, then <math>s</math>, alternately) will yield features (the basis vectors of <math>A</math>) similar to those learned using the sparse autoencoder.
+
Optimizing for this objective function (using the iterative method of optimizing for <math>A</math>, then <math>s</math>, alternately) will yield features (the basis vectors of <math>A</math>) similar to those learned using the sparse autoencoder. For more practical tips on implementing sparse coding, you may wish to refer to [[Exercise:Sparse Coding | the sparse coding exercise]]. For assistance with deriving the gradients, you may wish to refer to [[Deriving gradients using the backpropagation idea]].
== Topographic sparse coding ==
== Topographic sparse coding ==

Revision as of 05:56, 28 May 2011

Personal tools