https://github.com/kimhc6028/soft-decision-tree

pytorch implementation of "Distilling a Neural Network Into a Soft Decision Tree"
https://github.com/kimhc6028/soft-decision-tree

Last synced: about 2 months ago
JSON representation

pytorch implementation of "Distilling a Neural Network Into a Soft Decision Tree"

• Host: GitHub
• URL: https://github.com/kimhc6028/soft-decision-tree
• Owner: kimhc6028
• License: bsd-3-clause
• Created: 2017-12-07T23:31:08.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-12-23T09:53:45.000Z (over 5 years ago)
• Last Synced: 2024-07-22T16:52:16.929Z (2 months ago)
• Language: Python
• Homepage: https://arxiv.org/pdf/1711.09784.pdf
• Size: 112 KB
• Stars: 280
• Watchers: 10
• Forks: 59
• Open Issues: 13
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Soft-Decision-Tree

Soft-Decision-Tree is the pytorch implementation of [Distilling a Neural Network Into a Soft Decision

Tree](https://arxiv.org/pdf/1711.09784.pdf), paper recently published on Arxiv about adopting decision tree algorithm into neural network.

"If we could take the knowledge acquired by the neural net and express the same knowledge in a model that relies on hierarchical decisions instead, explaining a particular decision would be much easier."



## Requirements

- python

- [pytorch](https://pytorch.org/)

## Result

I achieved 92.95% of test dataset accuracy on MNISTafter 40 epoches, without exploring enough of hyper-parameters (The paper achieved 94.45%). Higher accuracy might be achievable with searching hyper-parameters, or training longer epoches (if you can, please let me know :) )

## Usage

   $ python main.py