{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1708.02709","title":"Recent Trends in Deep Learning Based Natural Language Processing","created":"2017-08-09","cited_by_count":263},{"id":"1509.06569","title":"Tensorizing Neural Networks","created":"2015-09-22","cited_by_count":250},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"1802.08435","title":"Efficient Neural Audio Synthesis","created":"2018-02-23","cited_by_count":219},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"1906.06307","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","created":"2019-06-14","cited_by_count":96},{"id":"1910.13796","title":"Deep Learning vs. Traditional Computer Vision","created":"2019-10-30","cited_by_count":94},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79},{"id":"2010.15581","title":"The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research","created":"2020-10-22","cited_by_count":67},{"id":"1906.10732","title":"The Difficulty of Training Sparse Neural Networks","created":"2019-06-25","cited_by_count":62},{"id":"1908.09979","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","created":"2019-08-27","cited_by_count":56},{"id":"2107.03356","title":"M-FAC: Efficient Matrix-Free Approximations of Second-Order Information","created":"2021-07-07","cited_by_count":54},{"id":"1709.01134","title":"WRPN: Wide Reduced-Precision Networks","created":"2017-09-04","cited_by_count":51},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49},{"id":"2202.09844","title":"Sparsity Winning Twice: Better Robust Generalization from More Efficient Training","created":"2022-02-20","cited_by_count":41},{"id":"2009.11839","title":"A Gradient Flow Framework For Analyzing Network Pruning","created":"2020-09-24","cited_by_count":36},{"id":"1911.10988","title":"Sparsity through evolutionary pruning prevents neuronal networks from overfitting","created":"2019-11-07","cited_by_count":11},{"id":"1403.7151","title":"Understanding brain networks and brain organization","created":"2014-03-27","cited_by_count":6},{"id":"1803.08971","title":"Computational Power and the Social Impact of Artificial Intelligence","created":"2018-03-23","cited_by_count":5}],"next_cursor":null}