{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"1705.07857","title":"Real Time Image Saliency for Black Box Classifiers","created":"2017-05-22","cited_by_count":246},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"2002.10689","title":"A Theory of Usable Information Under Computational Constraints","created":"2020-02-25","cited_by_count":162},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"1907.07165","title":"Explaining Classifiers with Causal Concept Effect (CaCE)","created":"2019-07-16","cited_by_count":135},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131},{"id":"2001.00396","title":"Restricting the Flow: Information Bottlenecks for Attribution","created":"2020-01-02","cited_by_count":110},{"id":"1902.02960","title":"Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making","created":"2019-02-08","cited_by_count":109},{"id":"2008.06693","title":"Explainability in Deep Reinforcement Learning","created":"2020-08-15","cited_by_count":97},{"id":"2006.01855","title":"Aligning Superhuman AI with Human Behavior: Chess as a Model System","created":"2020-06-02","cited_by_count":79},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1706.04208","title":"Hybrid Reward Architecture for Reinforcement Learning","created":"2017-06-13","cited_by_count":58},{"id":"2010.12016","title":"Towards falsifiable interpretability research","created":"2020-10-22","cited_by_count":53},{"id":"1912.09007","title":"Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations","created":"2019-12-19","cited_by_count":50},{"id":"1912.12191","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","created":"2019-12-23","cited_by_count":50},{"id":"1609.05518","title":"Towards Deep Symbolic Reinforcement Learning","created":"2016-09-18","cited_by_count":42},{"id":"1811.12530","title":"Learning Finite State Representations of Recurrent Policy Networks","created":"2018-11-29","cited_by_count":37},{"id":"1907.05855","title":"DisCoRL: Continual Reinforcement Learning via Policy Distillation","created":"2019-07-11","cited_by_count":36},{"id":"2007.11500","title":"Debiasing Concept-based Explanations with Causal Analysis","created":"2020-07-22","cited_by_count":32},{"id":"1904.04520","title":"Regression Concept Vectors for Bidirectional Explanations in Histopathology","created":"2019-04-09","cited_by_count":31},{"id":"1911.11293","title":"Efficient Saliency Maps for Explainable AI","created":"2019-11-26","cited_by_count":30},{"id":"1906.06188","title":"Global and Local Interpretability for Cardiac MRI Classification","created":"2019-06-14","cited_by_count":29},{"id":"1910.01526","title":"Gated Linear Networks","created":"2019-09-30","cited_by_count":26},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22},{"id":"1901.08651","title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","created":"2019-01-24","cited_by_count":21},{"id":"2009.04374","title":"Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess","created":"2020-09-09","cited_by_count":15},{"id":"2012.02308","title":"Concept-based model explanations for Electronic Health Records","created":"2020-12-03","cited_by_count":14},{"id":"1905.11852","title":"EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction","created":"2019-05-28","cited_by_count":13},{"id":"1804.08597","title":"Towards Symbolic Reinforcement Learning with Common Sense","created":"2018-04-23","cited_by_count":12},{"id":"1907.08321","title":"SentiMATE: Learning to play Chess through Natural Language Processing","created":"2019-07-18","cited_by_count":9},{"id":"1809.09369","title":"S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning","created":"2018-09-25","cited_by_count":6},{"id":"1908.06660","title":"Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data","created":"2019-08-19","cited_by_count":5},{"id":"2005.06223","title":"DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics","created":"2020-05-13","cited_by_count":5},{"id":"2011.06665","title":"Domain-Level Explainability -- A Challenge for Creating Trust in Superhuman AI Strategies","created":"2020-11-12","cited_by_count":5},{"id":"1904.08155","title":"Deep learning investigation for chess player attention prediction using eye-tracking and game data","created":"2019-04-17","cited_by_count":3},{"id":"2006.09128","title":"Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability","created":"2020-06-16","cited_by_count":3}],"next_cursor":null}