Home

Awesome

<h1 align="center"> Hierarchical neural-net interpretations (ACD) 🧠</h1> <p align="center"> Produces hierarchical interpretations for a single prediction made by a pytorch neural network. Official code for <i>Hierarchical interpretations for neural network predictions</i> (ICLR 2019 <a href="https://openreview.net/pdf?id=SkEqro0ctQ">pdf</a>). </p> <p align="center"> <img src="https://img.shields.io/badge/license-mit-blue.svg"> <img src="https://img.shields.io/badge/python-3.6--3.8-blue"> <img src="https://img.shields.io/badge/pytorch-1.0%2B-blue"> <img src="https://img.shields.io/github/checks-status/csinva/hierarchical-dnn-interpretations/master"> <img src="https://img.shields.io/pypi/v/acd?color=orange"> <img src="https://static.pepy.tech/personalized-badge/acd?period=total&units=none&left_color=gray&right_color=orange&left_text=downloads"> </p> <p align="center"> <a href="https://csinva.io/hierarchical-dnn-interpretations/">Documentation</a> • <a href="https://github.com/csinva/hierarchical-dnn-interpretations/tree/master/reproduce_figs">Demo notebooks</a> </p> <p align="center"> <i>Note: this repo is actively maintained. For any questions please file an issue.</i> </p>

examples/documentation

Inspecting NLP sentiment modelsDetecting adversarial examplesAnalyzing imagenet models

notes on using ACD on your own data

related work

reference

@inproceedings{
   singh2019hierarchical,
   title={Hierarchical interpretations for neural network predictions},
   author={Chandan Singh and W. James Murdoch and Bin Yu},
   booktitle={International Conference on Learning Representations},
   year={2019},
   url={https://openreview.net/forum?id=SkEqro0ctQ},
}