Feature extraction using convolution

From Ufldl

Jump to: navigation, search
m (Fast Feature Learning and Extraction)
(Weight Sharing (Convolution))
Line 15: Line 15:
== Weight Sharing (Convolution) ==
== Weight Sharing (Convolution) ==
-
Natural images have the property of being stationary, that is, the statistics of one part of the image is the same as any other part. This suggests that the features that we learn at one part of the image can also be applicable to other regions -- i.e., we should have the same features at all locations.
+
Natural images have the property of being stationary, that is, 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 applicable to other regions -- i.e., we should have the same features at all locations.
In practice, this is 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.
In practice, this is 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 05:10, 22 May 2011

Personal tools