{"list":"other","total":58,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"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":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872},{"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":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"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":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"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":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1812.03596","title":"Task-Free Continual Learning","created":"2018-12-10","cited_by_count":221},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1910.06562","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","created":"2019-10-15","cited_by_count":207},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"1302.4389","title":"Maxout Networks","created":"2013-02-18","cited_by_count":187},{"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":"1805.09733","title":"Towards Robust Evaluations of Continual Learning","created":"2018-05-24","cited_by_count":148},{"id":"2002.06487","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","created":"2020-02-16","cited_by_count":117},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2007.07617","title":"SpaceNet: Make Free Space For Continual Learning","created":"2020-07-15","cited_by_count":53},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46},{"id":"1806.05421","title":"Selfless Sequential Learning","created":"2018-06-14","cited_by_count":44},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40},{"id":"1910.06943","title":"The Local Elasticity of Neural Networks","created":"2019-10-15","cited_by_count":37},{"id":"2007.07011","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","created":"2020-07-14","cited_by_count":29},{"id":"1811.06626","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","created":"2018-11-15","cited_by_count":24},{"id":"2004.11545","title":"Dropout as an Implicit Gating Mechanism For Continual Learning","created":"2020-04-24","cited_by_count":24},{"id":"2101.00926","title":"CLeaR: An Adaptive Continual Learning Framework for Regression Tasks","created":"2021-01-04","cited_by_count":22},{"id":"2203.06514","title":"Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations","created":"2022-03-12","cited_by_count":19},{"id":"2008.13363","title":"Extreme Memorization via Scale of Initialization","created":"2020-08-31","cited_by_count":18},{"id":"2010.11775","title":"Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity","created":"2020-10-22","cited_by_count":18},{"id":"2003.07417","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","created":"2020-03-16","cited_by_count":17},{"id":"2112.03257","title":"Functional Regularization for Reinforcement Learning via Learned Fourier Features","created":"2021-12-06","cited_by_count":17},{"id":"2301.05058","title":"Sparse Coding in a Dual Memory System for Lifelong Learning","created":"2022-12-28","cited_by_count":16},{"id":"2007.00811","title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks","created":"2020-07-01","cited_by_count":12},{"id":"2107.07617","title":"Algorithmic insights on continual learning from fruit flies","created":"2021-07-15","cited_by_count":11},{"id":"2303.11934","title":"Sparse Distributed Memory is a Continual Learner","created":"2023-03-20","cited_by_count":11},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9},{"id":"1707.08316","title":"Learning Sparse Representations in Reinforcement Learning with Sparse Coding","created":"2017-07-26","cited_by_count":5},{"id":"2211.04624","title":"Cold Start Streaming Learning for Deep Networks","created":"2022-11-09","cited_by_count":3}],"next_cursor":null}