{"list":"other","total":70,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1711.09601","title":"Memory Aware Synapses: Learning what (not) to forget","created":"2017-11-27","cited_by_count":1105},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1703.08475","title":"Overcoming Catastrophic Forgetting by Incremental Moment Matching","created":"2017-03-24","cited_by_count":243},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1812.03596","title":"Task-Free Continual Learning","created":"2018-12-10","cited_by_count":221},{"id":"1805.07810","title":"Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting","created":"2018-05-20","cited_by_count":201},{"id":"1805.12369","title":"Reinforced Continual Learning","created":"2018-05-31","cited_by_count":186},{"id":"1711.10563","title":"FearNet: Brain-Inspired Model for Incremental Learning","created":"2017-11-28","cited_by_count":177},{"id":"1507.06228","title":"Training Very Deep Networks","created":"2015-07-22","cited_by_count":173},{"id":"2001.00689","title":"A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning","created":"2020-01-03","cited_by_count":134},{"id":"1611.01929","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","created":"2016-11-07","cited_by_count":106},{"id":"1712.00961","title":"Learning Independent Causal Mechanisms","created":"2017-12-04","cited_by_count":105},{"id":"1809.10635","title":"Generative replay with feedback connections as a general strategy for continual learning","created":"2018-09-27","cited_by_count":104},{"id":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"2009.01797","title":"A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning","created":"2020-09-03","cited_by_count":87},{"id":"1606.07839","title":"Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles","created":"2016-06-24","cited_by_count":77},{"id":"1812.09111","title":"Generative Models from the perspective of Continual Learning","created":"2018-12-21","cited_by_count":69},{"id":"1902.05522","title":"Superposition of many models into one","created":"2019-02-14","cited_by_count":64},{"id":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63},{"id":"1803.10123","title":"Task Agnostic Continual Learning Using Online Variational Bayes","created":"2018-03-27","cited_by_count":61},{"id":"1710.10368","title":"Deep Generative Dual Memory Network for Continual Learning","created":"2017-10-28","cited_by_count":59},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58},{"id":"1607.01097","title":"AdaNet: Adaptive Structural Learning of Artificial Neural Networks","created":"2016-07-05","cited_by_count":54},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43},{"id":"1902.00255","title":"Policy Consolidation for Continual Reinforcement Learning","created":"2019-02-01","cited_by_count":39},{"id":"1805.10966","title":"Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization","created":"2018-05-28","cited_by_count":38},{"id":"2110.10067","title":"CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents","created":"2021-10-19","cited_by_count":38},{"id":"2010.13303","title":"Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning","created":"2020-10-26","cited_by_count":35},{"id":"1612.03770","title":"Neurogenesis Deep Learning","created":"2016-12-12","cited_by_count":32},{"id":"1906.10667","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","created":"2019-06-25","cited_by_count":30},{"id":"1703.10371","title":"Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks","created":"2017-03-30","cited_by_count":29},{"id":"1906.04452","title":"Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer","created":"2019-06-11","cited_by_count":26},{"id":"1910.01526","title":"Gated Linear Networks","created":"2019-09-30","cited_by_count":26},{"id":"1706.03475","title":"Confident Multiple Choice Learning","created":"2017-06-12","cited_by_count":24},{"id":"1905.10112","title":"Continual Reinforcement Learning in 3D Non-stationary Environments","created":"2019-05-24","cited_by_count":22},{"id":"1908.02984","title":"Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation","created":"2019-08-08","cited_by_count":22},{"id":"1908.08017","title":"Knowledge transfer in deep block-modular neural networks","created":"2019-07-24","cited_by_count":14},{"id":"1902.09434","title":"S-TRIGGER: Continual State Representation Learning via Self-Triggered Generative Replay","created":"2019-02-25","cited_by_count":7},{"id":"1606.02355","title":"Active Long Term Memory Networks","created":"2016-06-07","cited_by_count":4}],"next_cursor":null}