Add some new features for ANN #146
Open
Conversation
This file contains hidden or 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 dropout layer and its corresponding model. - test it on Iris dataset with dropout rate setting as 0.2 get 0.96 accuracy if we do not use the dropout layer (dropout rate = 0) the accuracy is 0.88.
- add embedding layer and its corresponding model for ANN - this is NOT a default setting for the construction of MLP forward topology
- add relu and tanh activation methods - use them in feed forward topology part (path: `alink/operator/common/classification/ann/FeedForwardTopology.java`) - use sigmoid as default one
|
|
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
To extend the universal support of ANN model I add the following new features for ANN:
Please check and comment on those code : )