[mlpack-git] [mlpack] Added DropConnect Layer and its tests.Fixes #413 (#552)
abhinavchanda
notifications at github.com
Fri Mar 4 16:00:15 EST 2016
DropConnect Layer is based on Linear Layer, but with the difference that the weight matrix is multiplied by the random mask.I have also added tests, in which , the network architechture and size of hidden layer is same as that of the dropout layer in tests/feedforward_network_test.cpp.On my systems, the three tests are giving these classificationErrors:
Dropout DropConnect
1 0.0729288 0.0729288
2 0.02 0.02
3 0.134 0.068
You can view, comment on, or merge this pull request online at:
https://github.com/mlpack/mlpack/pull/552
-- Commit Summary --
* Added drop_connect_layer.hpp. Fixes issue #413.
* Added tests for drop_connect_layer.hpp
-- File Changes --
A src/mlpack/methods/ann/layer/drop_connect_layer.hpp (382)
M src/mlpack/tests/feedforward_network_test.cpp (128)
-- Patch Links --
https://github.com/mlpack/mlpack/pull/552.patch
https://github.com/mlpack/mlpack/pull/552.diff
---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/552
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160304/d4291722/attachment.html>
More information about the mlpack-git
mailing list