Skip to content
This repository has been archived by the owner on Jul 10, 2021. It is now read-only.

Support to transfer weights from autoencoder to mlp #58

Merged
merged 3 commits into from
May 23, 2015
Merged

Support to transfer weights from autoencoder to mlp #58

merged 3 commits into from
May 23, 2015

Conversation

alexjc
Copy link
Member

@alexjc alexjc commented May 22, 2015

This acts as a form of unsupervised layer-wise pretraining.

@alexjc alexjc mentioned this pull request May 22, 2015
Closed
@coveralls
Copy link

Coverage Status

Coverage decreased (-0.31%) to 99.69% when pulling 8a9701a on pretrain into d221c57 on master.

@coveralls
Copy link

Coverage Status

Coverage remained the same at 100.0% when pulling 9485e14 on pretrain into d221c57 on master.

@coveralls
Copy link

Coverage Status

Coverage remained the same at 100.0% when pulling 88e1336 on pretrain into d221c57 on master.

1 similar comment
@coveralls
Copy link

Coverage Status

Coverage remained the same at 100.0% when pulling 88e1336 on pretrain into d221c57 on master.

alexjc added a commit that referenced this pull request May 23, 2015
@alexjc
Merge pull request #58 from aigamedev/pretrain
84fbaea 
Support to transfer weights from autoencoder to mlp
@alexjc alexjc merged commit 84fbaea into master May 23, 2015
@alexjc
Copy link
Member Author

alexjc commented May 23, 2015

Merging as it contains a fix for a bigger bug with best_valid_error.

@alexjc alexjc deleted the pretrain branch May 23, 2015 11:38
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Reviewers
No reviews
Assignees
No one assigned
Labels
enhancement
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@alexjc @coveralls