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

Deeper nets #42

Open
gngdb opened this issue Feb 28, 2015 · 2 comments
Open

Deeper nets #42

gngdb opened this issue Feb 28, 2015 · 2 comments
Labels
ready
Milestone
Pylearn2 models

Comments

@gngdb
Copy link
Member

gngdb commented Feb 28, 2015

Looking at the network mentioned on the forum using CXXNet, they're using a much deeper network than ours. Working from their network as an example and looking at the original Hinton Imagenet paper. Will call the network deeper_net.yaml.
@gngdb gngdb added this to the Pylearn2 models milestone Feb 28, 2015
@gngdb gngdb added the ready label Feb 28, 2015
@gngdb
Copy link
Member Author

gngdb commented Mar 2, 2015

Actually, appears is only slightly deeper than ours, they just have to define every max pooling operation as a layer as well.

@scottclowe
Copy link
Member

This is 3 convolutions and 2 or 3 MLPs, right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
ready
Projects
None yet
Milestone
Pylearn2 models
Development

No branches or pull requests
2 participants
@gngdb @scottclowe