multitask classifier #357
Open
multitask classifier #357
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
for more information, see https://pre-commit.ci
- Added Multitask_Transfer.ipynb to evaluate transfer learning efficiency. - Tests SPORF model on MNIST ➔ FashionMNIST transfer. - Focus on extremely small target training ratios (0.1%, 0.2%, 0.5%, 1%). - Results show successful transfer improvement at 0.2% (16 samples). - Notebook includes package setup, model class, experiments, and results table.
Author
|
This PR adds a new Jupyter Notebook to evaluate transfer learning efficiency using the MultitaskForestClassifier (SPORF model). We test transfer from MNIST to FashionMNIST under extremely small target data ratios (0.1%, 0.2%, 0.5%, 1%). And our results show that at 0.2% (16 samples), transfer learning improves accuracy, while at other ratios results are mostly noise. |
Transfer experiment with MORF, and the result shown that Transfer learning using MORF is effective when training data is extremely limited.
Author
|
New update with MORF and transfer learning using MORF is effective when training data is extremely limited. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Reference Issues/PRs
What does this implement/fix? Explain your changes.
Any other comments?