Skip to content

Edits to SdA tutorial for clarity. #51

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.

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

Merged
merged 3 commits into from
Apr 7, 2015
Merged

Conversation

mspandit
Copy link
Contributor

@mspandit mspandit commented Nov 3, 2014

No description provided.

Once all layers are pre-trained, the network goes through a second stage
of training called **fine-tuning**. Here we consider **supervised fine-tuning**
of training called **fine-tuning**,
where we want to minimize prediction error on a supervised task.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That one was correct, since unsupervised fine-tuning can also exist.

@lamblin
Copy link
Member

lamblin commented Mar 31, 2015

I'm really sorry I forgot that this last request was pending.
If you do not have time anymore to address my last comments, just let me know and I'll take care of that.
Thanks again for your help!

@mspandit
Copy link
Contributor Author

mspandit commented Apr 7, 2015

No problem. I've pulled from master and addressed your points.

@lamblin
Copy link
Member

lamblin commented Apr 7, 2015

Thanks a lot!

lamblin added a commit that referenced this pull request Apr 7, 2015
Edits to SdA tutorial for clarity.
@lamblin lamblin merged commit 20897f5 into lisa-lab:master Apr 7, 2015
taneishi pushed a commit to taneishi/DBN that referenced this pull request Nov 28, 2019
Edits to SdA tutorial for clarity.
taneishi pushed a commit to taneishi/DBN that referenced this pull request Feb 13, 2020
Edits to SdA tutorial for clarity.

Former-commit-id: 9ba8731
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants