Mercurial > pylearn

annotate activation.py @ 501:4fb6f7320518

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
N-class logistic regression top-layer works
author Joseph Turian <turian@gmail.com>
date Tue, 28 Oct 2008 13:54:01 -0400
parents f13847478c6d
children
rev   line source
496
f13847478c6d A few more ideas, in comments
Joseph Turian <turian@gmail.com>
parents:
diff changeset
1 """
f13847478c6d A few more ideas, in comments
Joseph Turian <turian@gmail.com>
parents:
diff changeset
2 Activation functions.
f13847478c6d A few more ideas, in comments
Joseph Turian <turian@gmail.com>
parents:
diff changeset
3
f13847478c6d A few more ideas, in comments
Joseph Turian <turian@gmail.com>
parents:
diff changeset
4 @todo: Make an Activation function class, with a particular contract.
f13847478c6d A few more ideas, in comments
Joseph Turian <turian@gmail.com>
parents:
diff changeset
5 That way, we can swap in Activation functions in our algorithms.
f13847478c6d A few more ideas, in comments
Joseph Turian <turian@gmail.com>
parents:
diff changeset
6 """