{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"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":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1903.05662","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","created":"2019-03-13","cited_by_count":231},{"id":"1905.10083","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","created":"2019-05-24","cited_by_count":228},{"id":"1911.02549","title":"MLPerf Inference Benchmark","created":"2019-11-06","cited_by_count":199},{"id":"1511.06393","title":"Fixed Point Quantization of Deep Convolutional Networks","created":"2015-11-19","cited_by_count":143},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1801.06601","title":"CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs","created":"2018-01-19","cited_by_count":121},{"id":"1709.01921","title":"Distributed Deep Neural Networks over the Cloud, the Edge and End Devices","created":"2017-09-06","cited_by_count":120},{"id":"1711.07128","title":"Hello Edge: Keyword Spotting on Microcontrollers","created":"2017-11-20","cited_by_count":110},{"id":"1509.09308","title":"Fast Algorithms for Convolutional Neural Networks","created":"2015-09-30","cited_by_count":102},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"2003.04821","title":"Benchmarking TinyML Systems: Challenges and Direction","created":"2020-03-10","cited_by_count":91},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"1705.06963","title":"A Survey of Neuromorphic Computing and Neural Networks in Hardware","created":"2017-05-19","cited_by_count":85},{"id":"1910.06663","title":"AI Benchmark: All About Deep Learning on Smartphones in 2019","created":"2019-10-15","cited_by_count":77},{"id":"1509.08971","title":"Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition","created":"2015-09-29","cited_by_count":67},{"id":"1701.00299","title":"Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution","created":"2017-01-02","cited_by_count":59},{"id":"1912.03413","title":"Dissecting the Graphcore IPU Architecture via Microbenchmarking","created":"2019-12-07","cited_by_count":47},{"id":"1706.01406","title":"NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representations of Feature Maps","created":"2017-06-05","cited_by_count":39},{"id":"1511.06488","title":"Resiliency of Deep Neural Networks under Quantization","created":"2015-11-20","cited_by_count":35},{"id":"2012.11233","title":"Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead","created":"2020-12-21","cited_by_count":34},{"id":"1807.03010","title":"XNOR Neural Engine: a Hardware Accelerator IP for 21.6 fJ/op Binary Neural Network Inference","created":"2018-07-09","cited_by_count":30},{"id":"2009.00993","title":"Survey of Machine Learning Accelerators","created":"2020-09-01","cited_by_count":29},{"id":"1811.02883","title":"SCALE-Sim: Systolic CNN Accelerator Simulator","created":"2018-10-16","cited_by_count":26},{"id":"1910.01059","title":"An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications","created":"2019-10-02","cited_by_count":26},{"id":"1604.03168","title":"Hardware-oriented Approximation of Convolutional Neural Networks","created":"2016-04-11","cited_by_count":20},{"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":"1707.09952","title":"Multiscale Co-Design Analysis of Energy, Latency, Area, and Accuracy of a ReRAM Analog Neural Training Accelerator","created":"2017-07-31","cited_by_count":15},{"id":"1804.05554","title":"BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOS","created":"2018-04-16","cited_by_count":10},{"id":"1902.01492","title":"Optimally Scheduling CNN Convolutions for Efficient Memory Access","created":"2019-02-04","cited_by_count":10},{"id":"2011.01713","title":"CUTIE: Beyond PetaOp/s/W Ternary DNN Inference Acceleration with Better-than-Binary Energy Efficiency","created":"2020-11-03","cited_by_count":10},{"id":"1704.04313","title":"CBinfer: Change-Based Inference for Convolutional Neural Networks on Video Data","created":"2017-04-14","cited_by_count":8},{"id":"1606.04209","title":"A Systematic Approach to Blocking Convolutional Neural Networks","created":"2016-06-14","cited_by_count":7},{"id":"1912.12167","title":"Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators","created":"2019-12-18","cited_by_count":6},{"id":"1605.03621","title":"ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks using Angle Sensitive Pixels","created":"2016-05-11","cited_by_count":4},{"id":"1905.03592","title":"AI Enabling Technologies: A Survey","created":"2019-05-08","cited_by_count":3},{"id":"1404.1320","title":"Draining our Glass: An Energy and Heat Characterization of Google Glass","created":"2014-03-26","cited_by_count":2},{"id":"2007.09963","title":"Improving Memory Utilization in Convolutional Neural Network Accelerators","created":"2020-07-20","cited_by_count":2}],"next_cursor":null}