Visual Summary of Value-level Feature Attribution in Prediction Classes with Recurrent Neural Networks
ViSFA helps to understand how recurrent neural networks produce final predictions. It's an interactive system that visually summarizes feature attribution over time for different feature values.
For feature attribution, I trained this biLSTM model with the attention mechanism.
Cite our paper ViSFA
@misc{wang2020visual,
title={Visual Summary of Value-level Feature Attribution in Prediction Classes with Recurrent Neural Networks},
author={Chuan Wang and Xumeng Wang and Kwan-Liu Ma},
year={2020},
eprint={2001.08379},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
}
Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE for more information.
Project Link: https://github.com/nauhc/hyppersteer