Feature extraction using convolution
From Ufldl
(→Weight Sharing (Convolution)) |
(→Weight Sharing (Convolution)) |
||
Line 15: | Line 15: | ||
== Weight Sharing (Convolution) == | == Weight Sharing (Convolution) == | ||
- | 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 | + | 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. |
<!-- | <!-- | ||
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. |