Feature extraction using convolution

From Ufldl

Jump to: navigation, search
(Weight Sharing (Convolution))
(Convolutions)
Line 15: Line 15:
== Convolutions ==
== Convolutions ==
-
Natural images have the property of being '''stationary''', meaning that the statistics of one part of the image are the same as any other part.  This suggests that the features that we learn at one part of the image can also be applied to other regions--i.e., we can use the same features at all locations.  
+
Natural images have the property of being '''stationary''', meaning that the statistics of one part of the image are the same as any other part.  This suggests that the features that we learn at one part of the image can also be applied to other parts of the image, and we can use the same features at all locations.  
<!--
<!--
To capture this idea of learning the same features "everywhere in the image," one option is to add an additional  added as an additional constraint known as weight sharing (tying) between the hidden units at different locations. If one chooses to have the same hidden unit replicated at every possible location, this turns out to be equivalent to a convolution of the feature (as a filter) on the image.
To capture this idea of learning the same features "everywhere in the image," one option is to add an additional  added as an additional constraint known as weight sharing (tying) between the hidden units at different locations. If one chooses to have the same hidden unit replicated at every possible location, this turns out to be equivalent to a convolution of the feature (as a filter) on the image.

Revision as of 18:13, 27 May 2011

Personal tools