Interpretability

Mining Object Parts From CNNs via Active Question-Answering CVPR 2017 Streaming Weak Submodularity: Interpreting Neural Networks on the Fly NeurIPS 2017 Fast and Flexible Monotonic Functions with Ensembles of Lattices NeurIPS 2016 Inverting Visual Representations With Convolutional Networks CVPR 2016 Monotonic Calibrated Interpolated Look-Up Tables JMLR 2016 Synthesizing the preferred inputs for neurons in neural networks via deep generator networks NeurIPS 2016 Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction NeurIPS 2015 Principal Differences Analysis: Interpretable Characterization of Differences between Distributions NeurIPS 2015 Understanding Classifier Errors by Examining Influential Neighbors CVPR 2015 Partition-wise Linear Models NeurIPS 2014 Understanding variable importances in forests of randomized trees NeurIPS 2013 Interpreting the neural code with Formal Concept Analysis NeurIPS 2008