{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"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":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1911.03852","title":"HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks","created":"2019-11-10","cited_by_count":261},{"id":"1409.2329","title":"Recurrent Neural Network Regularization","created":"2014-09-08","cited_by_count":189},{"id":"1609.01454","title":"Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling","created":"2016-09-06","cited_by_count":137},{"id":"1611.01462","title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","created":"2016-11-04","cited_by_count":92},{"id":"1611.01576","title":"Quasi-Recurrent Neural Networks","created":"2016-11-05","cited_by_count":87},{"id":"1709.02755","title":"Simple Recurrent Units for Highly Parallelizable Recurrence","created":"2017-09-08","cited_by_count":61},{"id":"1708.08917","title":"CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices","created":"2017-08-29","cited_by_count":55},{"id":"1910.02366","title":"Splitting Steepest Descent for Growing Neural Architectures","created":"2019-10-06","cited_by_count":55},{"id":"1905.12107","title":"SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers","created":"2019-05-28","cited_by_count":52},{"id":"1708.06834","title":"Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks","created":"2017-08-22","cited_by_count":49},{"id":"1510.01722","title":"Structured Transforms for Small-Footprint Deep Learning","created":"2015-10-06","cited_by_count":42},{"id":"2005.11138","title":"TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids","created":"2020-05-20","cited_by_count":42},{"id":"1705.07283","title":"Structured Bayesian Pruning via Log-Normal Multiplicative Noise","created":"2017-05-20","cited_by_count":39},{"id":"1901.02358","title":"FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network","created":"2019-01-08","cited_by_count":38},{"id":"1607.03474","title":"Recurrent Highway Networks","created":"2016-07-12","cited_by_count":37},{"id":"1705.08052","title":"Compressing Recurrent Neural Network with Tensor Train","created":"2017-05-23","cited_by_count":28},{"id":"1811.00641","title":"Online Embedding Compression for Text Classification using Low Rank Matrix Factorization","created":"2018-11-01","cited_by_count":22},{"id":"1810.02309","title":"Learning Compressed Transforms with Low Displacement Rank","created":"2018-10-04","cited_by_count":19},{"id":"1704.06877","title":"Learning to Skim Text","created":"2017-04-23","cited_by_count":18},{"id":"1709.05027","title":"Learning Intrinsic Sparse Structures within Long Short-Term Memory","created":"2017-09-15","cited_by_count":18},{"id":"2005.08098","title":"Systolic Tensor Array: An Efficient Structured-Sparse GEMM Accelerator for Mobile CNN Inference","created":"2020-05-16","cited_by_count":17},{"id":"1711.02085","title":"Neural Speed Reading via Skim-RNN","created":"2017-11-06","cited_by_count":14},{"id":"1703.10722","title":"Factorization tricks for LSTM networks","created":"2017-03-31","cited_by_count":13},{"id":"2004.10936","title":"PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices","created":"2020-04-23","cited_by_count":12},{"id":"1906.02876","title":"Compressing RNNs for IoT devices by 15-38x using Kronecker Products","created":"2019-06-07","cited_by_count":11},{"id":"1902.11128","title":"FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning","created":"2019-02-27","cited_by_count":10},{"id":"1911.12385","title":"DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling","created":"2019-11-27","cited_by_count":10},{"id":"1512.09194","title":"Exploiting Local Structures with the Kronecker Layer in Convolutional Networks","created":"2015-12-31","cited_by_count":7},{"id":"1902.02380","title":"Compression of Recurrent Neural Networks for Efficient Language Modeling","created":"2019-02-06","cited_by_count":7},{"id":"1906.06847","title":"Structured Pruning of Recurrent Neural Networks through Neuron Selection","created":"2019-06-17","cited_by_count":7},{"id":"2010.03193","title":"Rank and run-time aware compression of NLP Applications","created":"2020-10-06","cited_by_count":5},{"id":"1708.05963","title":"Neural Networks Compression for Language Modeling","created":"2017-08-20","cited_by_count":4},{"id":"1903.01531","title":"Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications","created":"2019-03-04","cited_by_count":4},{"id":"2001.08896","title":"Compressing Language Models using Doped Kronecker Products","created":"2020-01-24","cited_by_count":4},{"id":"1801.06274","title":"Mobile Machine Learning Hardware at ARM: A Systems-on-Chip (SoC) Perspective","created":"2018-01-19","cited_by_count":3},{"id":"1804.11239","title":"Structured Weight Matrices-Based Hardware Accelerators in Deep Neural Networks: FPGAs and ASICs","created":"2018-03-28","cited_by_count":3},{"id":"1911.01028","title":"Ternary MobileNets via Per-Layer Hybrid Filter Banks","created":"2019-11-04","cited_by_count":3},{"id":"1805.11233","title":"Retraining-Based Iterative Weight Quantization for Deep Neural Networks","created":"2018-05-29","cited_by_count":2},{"id":"1808.09029","title":"Pyramidal Recurrent Unit for Language Modeling","created":"2018-08-27","cited_by_count":2},{"id":"1810.12823","title":"DeepTwist: Learning Model Compression via Occasional Weight Distortion","created":"2018-10-30","cited_by_count":2},{"id":"1910.02558","title":"Pushing the limits of RNN Compression","created":"2019-10-04","cited_by_count":2},{"id":"1904.03302","title":"Measuring scheduling efficiency of RNNs for NLP applications","created":"2019-04-05","cited_by_count":1},{"id":"1906.04886","title":"Run-Time Efficient RNN Compression for Inference on Edge Devices","created":"2019-06-12","cited_by_count":1}],"next_cursor":null}