{"list":"other","total":73,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"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":"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":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"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":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"2103.17230","title":"Rainbow Memory: Continual Learning with a Memory of Diverse Samples","created":"2021-03-31","cited_by_count":273},{"id":"1810.12488","title":"Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines","created":"2018-10-30","cited_by_count":228},{"id":"2002.10211","title":"Mnemonics Training: Multi-Class Incremental Learning without Forgetting","created":"2020-02-24","cited_by_count":221},{"id":"1903.10145","title":"Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing","created":"2019-03-25","cited_by_count":191},{"id":"1904.03137","title":"Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning","created":"2019-04-05","cited_by_count":182},{"id":"1810.01256","title":"Continual Learning of Context-dependent Processing in Neural Networks","created":"2018-09-29","cited_by_count":179},{"id":"2002.08165","title":"Using Hindsight to Anchor Past Knowledge in Continual Learning","created":"2020-02-19","cited_by_count":161},{"id":"1506.02158","title":"Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference","created":"2015-06-06","cited_by_count":159},{"id":"2012.09823","title":"Continual Lifelong Learning in Natural Language Processing: A Survey","created":"2020-12-17","cited_by_count":152},{"id":"1805.09733","title":"Towards Robust Evaluations of Continual Learning","created":"2018-05-24","cited_by_count":148},{"id":"1910.14481","title":"Continual Unsupervised Representation Learning","created":"2019-10-31","cited_by_count":147},{"id":"1905.11614","title":"Uncertainty-based Continual Learning with Adaptive Regularization","created":"2019-05-28","cited_by_count":146},{"id":"2103.07113","title":"Training Networks in Null Space of Feature Covariance for Continual Learning","created":"2021-03-12","cited_by_count":143},{"id":"2001.00689","title":"A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning","created":"2020-01-03","cited_by_count":134},{"id":"1803.04386","title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","created":"2018-03-12","cited_by_count":133},{"id":"1903.12436","title":"From Variational to Deterministic Autoencoders","created":"2019-03-29","cited_by_count":133},{"id":"2002.00632","title":"Effective Diversity in Population Based Reinforcement Learning","created":"2020-02-03","cited_by_count":119},{"id":"2003.13726","title":"Continual Learning with Node-Importance based Adaptive Group Sparse Regularization","created":"2020-03-30","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":"2006.08205","title":"Learning Latent Space Energy-Based Prior Model","created":"2020-06-15","cited_by_count":104},{"id":"1906.02425","title":"Uncertainty-guided Continual Learning with Bayesian Neural Networks","created":"2019-06-06","cited_by_count":102},{"id":"1903.04476","title":"Continual Learning via Neural Pruning","created":"2019-03-11","cited_by_count":101},{"id":"1712.02390","title":"Noisy Natural Gradient as Variational Inference","created":"2017-12-06","cited_by_count":94},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"1907.10107","title":"Lifelong GAN: Continual Learning for Conditional Image Generation","created":"2019-07-23","cited_by_count":78},{"id":"1905.05301","title":"Hierarchically Structured Meta-learning","created":"2019-05-13","cited_by_count":68},{"id":"2006.07326","title":"CPR: Classifier-Projection Regularization for Continual Learning","created":"2020-06-12","cited_by_count":62},{"id":"1905.01240","title":"Information asymmetry in KL-regularized RL","created":"2019-05-03","cited_by_count":53},{"id":"1711.09874","title":"Divide-and-Conquer Reinforcement Learning","created":"2017-11-27","cited_by_count":48},{"id":"2106.08085","title":"Natural continual learning: success is a journey, not (just) a destination","created":"2021-06-15","cited_by_count":46},{"id":"2010.00352","title":"Meta-Consolidation for Continual Learning","created":"2020-10-01","cited_by_count":40},{"id":"1910.13631","title":"When does Diversity Help Generalization in Classification Ensembles?","created":"2019-10-30","cited_by_count":27},{"id":"2109.14035","title":"Formalizing the Generalization-Forgetting Trade-off in Continual Learning","created":"2021-09-28","cited_by_count":24},{"id":"1707.04588","title":"GLSR-VAE: Geodesic Latent Space Regularization for Variational AutoEncoder Architectures","created":"2017-07-14","cited_by_count":22},{"id":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20},{"id":"1909.05950","title":"Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning","created":"2019-09-11","cited_by_count":18},{"id":"2104.08604","title":"Lifelong Learning with Sketched Structural Regularization","created":"2021-04-17","cited_by_count":15},{"id":"2110.08855","title":"Online Continual Learning Via Candidates Voting","created":"2021-10-17","cited_by_count":15},{"id":"2009.04381","title":"Routing Networks with Co-training for Continual Learning","created":"2020-09-09","cited_by_count":14},{"id":"1912.02290","title":"Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning","created":"2019-12-04","cited_by_count":11},{"id":"1906.06635","title":"Conditional Computation for Continual Learning","created":"2019-06-16","cited_by_count":8},{"id":"2101.12136","title":"Self-Attention Meta-Learner for Continual Learning","created":"2021-01-28","cited_by_count":8},{"id":"1907.11452","title":"An Information-theoretic On-line Learning Principle for Specialization in Hierarchical Decision-Making Systems","created":"2019-07-26","cited_by_count":7},{"id":"2108.07887","title":"Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay","created":"2021-08-17","cited_by_count":7},{"id":"1802.08250","title":"SeNA-CNN: Overcoming Catastrophic Forgetting in Convolutional Neural Networks by Selective Network Augmentation","created":"2018-02-22","cited_by_count":4},{"id":"2011.01845","title":"Specialization in Hierarchical Learning Systems","created":"2020-11-03","cited_by_count":3},{"id":"2112.01713","title":"Contrastive Continual Learning with Feature Propagation","created":"2021-12-03","cited_by_count":3},{"id":"1809.01575","title":"Bounded Rational Decision-Making with Adaptive Neural Network Priors","created":"2018-09-04","cited_by_count":2},{"id":"1911.00348","title":"Hierarchical Expert Networks for Meta-Learning","created":"2019-10-31","cited_by_count":2},{"id":"2111.07928","title":"Target Layer Regularization for Continual Learning Using Cramer-Wold Generator","created":"2021-11-15","cited_by_count":1}],"next_cursor":null}