laura-rieger/deep-explanation-penalization
Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
Jupyter NotebookMIT
Stargazers
- alceubissotoUNICAMP
- alvarosnessKirkland, WA
- alvinwanSeattle
- anindyaspaul
- boykacShanghaiTech
- chr5tphrRIKEN
- cloud2010Shanghai Maritime University
- diggerduBytedance AI Lab
- Dimlife
- georgosgeorgosDTU Compute
- JacobARose
- jiaoyiningUNC-Chapel Hill
- jisoolee0123
- JSCBenTianjin University
- Juna2South Korea
- ldkong1205National University of Singapore
- LiangGou
- lijiazheng99King's College London
- LinkToPast1990
- maxidlHanover, Germany
- mohanhanmo
- Ngchenhao
- novioleoChengDu
- p16i127.0.0.1
- pushpendrapratapNew Delhi, India
- rohitgajawadaAtlanta, GA
- RuiWang1998@HeliXonProtein
- ryanchankhUniversity of Pennsylvania
- sebastian-lapuschkinFraunhofer Heinrich-Hertz-Institute
- shj1987WM
- thbuerg@Pheiron
- timothy22000London, UK
- TJKleinBerlin, Germany
- UgurKapUniversity of Tübingen
- vasoto@CERN
- yaodongyuUC Berkeley