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
- aatkinson@Microsoft , @maluuba
- adalisan
- alvin319San Francisco, CA
- arassadinNigniy Novgorod, Russia
- BentengMa
- calvinyong
- caoxu915683474@Lenovo Reasearch@BIT
- ChiShengChen
- csinvaSenior researcher
- data-datumArgentina
- expectopatronum
- fly51flyPRIS
- jamie-murdochBerkeley
- jklaiseUnited Kingdom
- jlevy44
- laura-riegerPostdoc
- m-ak
- MadhumitaSushil
- masoudhashemi@servicenow
- MicPieOpenBioML.org
- MortenHannemose
- msetzuPisa
- MuhammedHasanUC Irvine
- NickoDemaRobotics Research Engineer | StarLine
- normalct
- phymucs
- radao@scythe-robotics
- RicherMansXiaomi
- shuirugeNULL
- tt6746690MIT
- udemirezenTurkey
- uvafan
- vlad3996Minsk, Belarus
- vyraunMicrosoft
- xuanhan863Los Angeles, USA
- yuerongz