Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implement maxout layer #19

Open
subversive-owl opened this issue Oct 13, 2017 · 2 comments
Open

Implement maxout layer #19

subversive-owl opened this issue Oct 13, 2017 · 2 comments
Labels
enhancement

Comments

@subversive-owl
Copy link
Contributor

See Goodfellow 2013 for paper.
@drahnr
Copy link
Member

drahnr commented Oct 13, 2017 •
edited
Loading

I had a quick look on it, but it looks like max pooling in one dimension which are refered to as different modesl? I have yet to sit down and dig into the details.

nbigaouette pushed a commit to nbigaouette/juice that referenced this issue Aug 31, 2018
@drahnr
Merge pull request fff-rs#19 from spearow/wip-dropout
704c26a
@Amanita-muscaria
Copy link

Amanita-muscaria commented Jul 21, 2020 •
edited
Loading

Max pooling is moving a window over the input data and taking the maximum value at each step. A maxout neuron does inputs * weights and then outputs the maximum value of the result. So a max pool in a convolutional network would be equivalent to a maxout layer with all weights set to one and none of the weights are trainable

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@drahnr @Amanita-muscaria @subversive-owl