adding complex valued neural network #8
Merged
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
Add a structure to create Complex valued neural networks.
add a file with different examples of complex neural network behaviour
an equivalent to the "three" test for real numbered ff networks that ignores imaginary part.
alpmestan
added a commit
that referenced
this pull request
Oct 1, 2015
adding complex valued neural network
|
Thanks! I'm kind of hoping to rewrite hnn in a way to supports what you what out of the box though, but let's put your code here for now =) |
|
Meaning each transpose will be conjugae and transpose and things like that?
|
|
The idea would be to rely on some instance for the number type to do the right thing. |
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Outdated suggestions cannot be applied.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.
following our email conversation many examples and the full working structure for creating complex valued feed forward neural networks was commited. (note that complexsigmoid is the main function used here, and tanh is undefined for complex valued neural networks)