JonathanCrabbe/Dynamask
This repository contains the implementation of Dynamask, a method to identify the features that are salient for a model to issue its prediction when the data is represented in terms of time series. For more details on the theoretical side, please read our ICML 2021 paper: 'Explaining Time Series Predictions with Dynamic Masks'.
PythonMIT
Stargazers
- 545487677DP Technology
- 666WXY666Beijing University of Posts and Telecommunications
- anaramirliSaarbrücken, Germany
- cfeng783Siemens
- chang111National University of Singapore
- cinneesolMelbourne
- demoleiwangSalesforce
- Dolores2333HKUST
- DrShushen
- ENM1989
- evolu8
- February24-LeeSNU
- feribgToronto, Canada
- flambyParis
- guang7400613
- i6092467ETH Zurich
- Jabrielle0813
- jia-wei-zheng
- jklaiseUnited Kingdom
- lgstd
- lxy1108
- MengMaxFan
- natalialmg
- nilavraABB Corporate Research Center Germany
- owencqueenStanford, CA
- oz-mishli
- pauldebdeep9
- Peng-yuWangSJTU
- SamanthaWangdlETH Zurich
- Schuck9The University of Hong Kong
- ShawnKSThe Chinese University of Hong Kong, Shenzhen
- StevenL2017
- TheSnowGuruOffpista LTD
- WangDenghuiTJ
- yifeiSunny
- yoliaGothenburg