taolicheng/understanding-dnn

Visualization

• Olah, et al., "The Building Blocks of Interpretability", Distill, 2018. https://distill.pub/2018/building-blocks/
• Visualizing Representations: Deep Learning and Human Beings, Colah's Blog, http://colah.github.io/posts/2015-01-Visualizing-Representations/
• http://karpathy.github.io/2015/05/21/rnn-effectiveness/
• http://deeplearning.csail.mit.edu/presentation_tutorial_interpretability_slide.pdf
• Opening the Black Box of Deep Neural Networks via Information, Ravid Shwartz-Ziv, Naftali Tishby. arXiv:1703.00810
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman. arXiv:1312.6034

Sensitivity and Relevance Analysis

• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition, Grégoire Montavon, Sebastian Bach, Alexander Binder, Wojciech Samek, Klaus-Robert Müller. arXiv:1512.02479

Conferences and Workshops

• ML Interpretability for Scientific Discovery,ICML 2020 Workshop
• Uncertainty and Robustness in Deep Learning, ICML2019 Workshop
• ICLR2019
• NeurIPS2018 [Summary Notes]
  • Workshop Bayesian Deep Learning
  • Workshop Causal Learning
  • Workshop Interpretability and Robustness in Audio, Speech, and Language