Num embeddings #200
Merged
Num embeddings #200
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
…feats. Now the two changes that need to happen are: 1. add the activation funcion in the Encoding Layer itself and 2. Define the embedding process in the base models rather than the DiffSizeCatAndContEmbeddings and the SameSizeCatAndContEmbeddings wrappers
…edding layers. Needs to be added within the cat embed layers and then move to 2. Define the embedding process in the base models rather than the DiffSizeCatAndContEmbeddings and the SameSizeCatAndContEmbeddings wrappers
…dding layers. Now onto 2. Define the embedding process in the base models rather than the DiffSizeCatAndContEmbeddings and the SameSizeCatAndContEmbeddings wrappers
…ed to test the two classes manually and then change the main models accordingly
… Now I need to 1. Adjust docs. 2. Adjust/Fix tests. 3. Redo the examples. 4. Add new examples
… Just have an overall look at the code. 3. Re-do examples. 4. Have a look to the mkdocs
…ple 3. Review mkdocs
…otebook with num embeddings. 2. Review the docs 3. Test in all possible platforms. Nearly there...
…res. I want to increase the coverage for the deeptabular_utils module and we are done
…in multiple platforms
…version of the library
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Outdated suggestions cannot be applied.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.
Added two new methods to embed continuous columns, described in the paper: On Embeddings for Numerical Features in Tabular Deep Learning.
Namely:
This involved a series of adaptations to all existing models