Converting hessianfree to nengo #2
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
drasmuss
changed the title
Seanny123
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Just put this together quickly to show that the basic idea of converting from one to the other is feasible. Note that this just goes hessianfree --> nengo, which is definitely the easier direction (since the space of possible network structures is much larger in nengo).
You can see how it works in the
hf_to_nengofunction, but it's pretty straightforward. I just create an ensemble for each layer, and then connect the layers with the weight matrices learned in thehessianfreenetwork. Examples showing it works for feedforward and recurrent networks.