{"list":"other","total":67,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1404.0736","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","created":"2014-04-02","cited_by_count":306},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"1509.06569","title":"Tensorizing Neural Networks","created":"2015-09-22","cited_by_count":250},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"1412.6115","title":"Compressing Deep Convolutional Networks using Vector Quantization","created":"2014-12-18","cited_by_count":195},{"id":"1511.06530","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","created":"2015-11-20","cited_by_count":162},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"1511.06393","title":"Fixed Point Quantization of Deep Convolutional Networks","created":"2015-11-19","cited_by_count":143},{"id":"1606.05535","title":"Tensor Ring Decomposition","created":"2016-06-17","cited_by_count":127},{"id":"1804.03294","title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers","created":"2018-04-10","cited_by_count":120},{"id":"1505.06798","title":"Accelerating Very Deep Convolutional Networks for Classification and Detection","created":"2015-05-26","cited_by_count":109},{"id":"1702.04008","title":"Soft Weight-Sharing for Neural Network Compression","created":"2017-02-13","cited_by_count":99},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"2008.05441","title":"Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network","created":"2020-08-12","cited_by_count":74},{"id":"1611.06321","title":"Learning the Number of Neurons in Deep Networks","created":"2016-11-19","cited_by_count":69},{"id":"1908.08932","title":"Learning Filter Basis for Convolutional Neural Network Compression","created":"2019-08-23","cited_by_count":57},{"id":"1611.03214","title":"Ultimate tensorization: compressing convolutional and FC layers alike","created":"2016-11-10","cited_by_count":56},{"id":"2004.09031","title":"Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification","created":"2020-04-20","cited_by_count":53},{"id":"2107.12422","title":"Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework","created":"2021-07-26","cited_by_count":52},{"id":"1802.09052","title":"Wide Compression: Tensor Ring Nets","created":"2018-02-25","cited_by_count":50},{"id":"1711.02638","title":"Compression-aware Training of Deep Networks","created":"2017-11-07","cited_by_count":46},{"id":"1502.07209","title":"Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks","created":"2015-02-25","cited_by_count":45},{"id":"1502.04390","title":"Equilibrated adaptive learning rates for non-convex optimization","created":"2015-02-15","cited_by_count":42},{"id":"1906.00443","title":"Dimensionality compression and expansion in Deep Neural Networks","created":"2019-06-02","cited_by_count":38},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33},{"id":"1701.07148","title":"CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression","created":"2017-01-25","cited_by_count":30},{"id":"2009.10580","title":"Heuristic Rank Selection with Progressively Searching Tensor Ring Network","created":"2020-09-22","cited_by_count":28},{"id":"1905.10478","title":"Bayesian Tensorized Neural Networks with Automatic Rank Selection","created":"2019-05-24","cited_by_count":26},{"id":"1907.11900","title":"DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks","created":"2019-07-27","cited_by_count":26},{"id":"1801.07365","title":"Learning to Prune Filters in Convolutional Neural Networks","created":"2018-01-23","cited_by_count":25},{"id":"1812.02402","title":"Trained Rank Pruning for Efficient Deep Neural Networks","created":"2018-12-06","cited_by_count":23},{"id":"1509.06490","title":"Bayesian Tensor Regression","created":"2015-09-22","cited_by_count":21},{"id":"2007.06631","title":"T-Basis: a Compact Representation for Neural Networks","created":"2020-07-13","cited_by_count":21},{"id":"1802.02271","title":"Universal Deep Neural Network Compression","created":"2018-02-07","cited_by_count":19},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16},{"id":"2006.15938","title":"Hybrid Tensor Decomposition in Neural Network Compression","created":"2020-06-29","cited_by_count":15},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14},{"id":"2010.04963","title":"Block-term Tensor Neural Networks","created":"2020-10-10","cited_by_count":13},{"id":"1906.02876","title":"Compressing RNNs for IoT devices by 15-38x using Kronecker Products","created":"2019-06-07","cited_by_count":11},{"id":"1301.7619","title":"Rank regularization and Bayesian inference for tensor completion and extrapolation","created":"2013-01-31","cited_by_count":8},{"id":"2205.15307","title":"A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks","created":"2022-05-28","cited_by_count":8},{"id":"1805.01631","title":"Is Information in the Brain Represented in Continuous or Discrete Form?","created":"2018-05-04","cited_by_count":4},{"id":"2203.13444","title":"Vision Transformer Compression with Structured Pruning and Low Rank Approximation","created":"2022-03-25","cited_by_count":4},{"id":"2109.15200","title":"Semi-tensor Product-based TensorDecomposition for Neural Network Compression","created":"2021-09-30","cited_by_count":3},{"id":"2203.02617","title":"How to Train Unstable Looped Tensor Network","created":"2022-03-05","cited_by_count":3},{"id":"2206.01509","title":"Canonical convolutional neural networks","created":"2022-06-03","cited_by_count":3},{"id":"2206.08257","title":"Gradient Descent for Low-Rank Functions","created":"2022-06-16","cited_by_count":3},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3},{"id":"2006.08878","title":"CNN Acceleration by Low-rank Approximation with Quantized Factors","created":"2020-06-16","cited_by_count":1}],"next_cursor":null}