DeepExplain
by marcoancona
Pythonpushed about 6 years ago
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
AI summary
Neural network attribution framework
A framework for understanding how deep neural networks process input data to produce output
- stars
- 735
- forks
- 134
- watching
- 37