{"list":"other","total":65,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"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":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1611.08024","title":"EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces","created":"2016-11-23","cited_by_count":628},{"id":"1902.04885","title":"Federated Machine Learning: Concept and Applications","created":"2019-02-13","cited_by_count":412},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1410.0759","title":"cuDNN: Efficient Primitives for Deep Learning","created":"2014-10-03","cited_by_count":245},{"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":"1901.09504","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","created":"2019-01-28","cited_by_count":151},{"id":"1804.03230","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","created":"2018-04-09","cited_by_count":147},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1907.08349","title":"Convergence of Edge Computing and Deep Learning: A Comprehensive Survey","created":"2019-07-19","cited_by_count":120},{"id":"1712.01507","title":"Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Networks","created":"2017-12-05","cited_by_count":109},{"id":"1805.12549","title":"Channel Gating Neural Networks","created":"2018-05-29","cited_by_count":80},{"id":"2001.00138","title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning","created":"2020-01-01","cited_by_count":76},{"id":"1509.08971","title":"Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognition","created":"2015-09-29","cited_by_count":67},{"id":"2006.00622","title":"EEG-TCNet: An Accurate Temporal Convolutional Network for Embedded Motor-Imagery Brain-Machine Interfaces","created":"2020-05-31","cited_by_count":63},{"id":"1803.10615","title":"SqueezeNext: Hardware-Aware Neural Network Design","created":"2018-03-23","cited_by_count":61},{"id":"1612.00694","title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA","created":"2016-12-01","cited_by_count":52},{"id":"1909.05073","title":"PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices","created":"2019-09-06","cited_by_count":50},{"id":"1904.04421","title":"FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge","created":"2019-04-09","cited_by_count":48},{"id":"2002.04116","title":"Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks","created":"2020-02-10","cited_by_count":43},{"id":"1901.11211","title":"Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search","created":"2019-01-31","cited_by_count":38},{"id":"1910.13349","title":"E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings","created":"2019-10-29","cited_by_count":36},{"id":"2005.02563","title":"EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions","created":"2020-05-06","cited_by_count":36},{"id":"1908.11263","title":"PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors","created":"2019-08-29","cited_by_count":35},{"id":"1905.13082","title":"Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers","created":"2019-05-30","cited_by_count":33},{"id":"1907.02124","title":"Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?","created":"2019-07-03","cited_by_count":32},{"id":"2012.12206","title":"FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations","created":"2020-12-22","cited_by_count":32},{"id":"1902.02910","title":"AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling","created":"2019-02-08","cited_by_count":27},{"id":"1909.09709","title":"SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems","created":"2019-09-20","cited_by_count":27},{"id":"2001.03535","title":"AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs","created":"2020-01-06","cited_by_count":26},{"id":"2006.14815","title":"A Co-Design Framework of Neural Networks and Quantum Circuits Towards Quantum Advantage","created":"2020-06-26","cited_by_count":23},{"id":"2012.13113","title":"FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training","created":"2020-12-24","cited_by_count":23},{"id":"1808.01550","title":"Designing Adaptive Neural Networks for Energy-Constrained Image Classification","created":"2018-08-05","cited_by_count":18},{"id":"1911.03314","title":"FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things","created":"2019-11-08","cited_by_count":18},{"id":"1906.02256","title":"Butterfly Transform: An Efficient FFT Based Neural Architecture Design","created":"2019-06-05","cited_by_count":16},{"id":"2008.00698","title":"Anti-Bandit Neural Architecture Search for Model Defense","created":"2020-08-03","cited_by_count":16},{"id":"2005.08501","title":"VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization","created":"2020-05-18","cited_by_count":15},{"id":"1809.01330","title":"ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions","created":"2018-09-05","cited_by_count":10},{"id":"1811.07755","title":"Building Efficient Deep Neural Networks with Unitary Group Convolutions","created":"2018-11-19","cited_by_count":9},{"id":"1911.07446","title":"NAIS: Neural Architecture and Implementation Search and its Applications in Autonomous Driving","created":"2019-11-18","cited_by_count":9},{"id":"2004.03804","title":"HybridDNN: A Framework for High-Performance Hybrid DNN Accelerator Design and Implementation","created":"2020-04-08","cited_by_count":9},{"id":"2005.07137","title":"ChewBaccaNN: A Flexible 223 TOPS/W BNN Accelerator","created":"2020-05-12","cited_by_count":9},{"id":"1901.10584","title":"Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach","created":"2019-01-29","cited_by_count":8},{"id":"2004.11690","title":"Q-EEGNet: an Energy-Efficient 8-bit Quantized Parallel EEGNet Implementation for Edge Motor-Imagery Brain--Machine Interfaces","created":"2020-04-24","cited_by_count":8},{"id":"1804.06404","title":"Are FPGAs Suitable for Edge Computing?","created":"2018-04-17","cited_by_count":7},{"id":"1808.04311","title":"Design Flow of Accelerating Hybrid Extremely Low Bit-width Neural Network in Embedded FPGA","created":"2018-07-31","cited_by_count":7},{"id":"2001.11854","title":"NASS: Optimizing Secure Inference via Neural Architecture Search","created":"2020-01-30","cited_by_count":7},{"id":"2003.06700","title":"CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way","created":"2020-03-14","cited_by_count":7},{"id":"2002.07136","title":"Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations","created":"2020-02-17","cited_by_count":5},{"id":"1908.06869","title":"XSP: Across-Stack Profiling and Analysis of Machine Learning Models on GPUs","created":"2019-08-19","cited_by_count":4},{"id":"1803.09004","title":"Face Recognition with Hybrid Efficient Convolution Algorithms on FPGAs","created":"2018-03-23","cited_by_count":3},{"id":"2006.05181","title":"Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs","created":"2020-06-09","cited_by_count":3},{"id":"2003.01551","title":"A New MRAM-based Process In-Memory Accelerator for Efficient Neural Network Training with Floating Point Precision","created":"2020-03-02","cited_by_count":2},{"id":"2005.03775","title":"Optimizing Temporal Convolutional Network inference on FPGA-based accelerators","created":"2020-05-07","cited_by_count":2},{"id":"1811.09737","title":"Frustrated with Replicating Claims of a Shared Model? A Solution","created":"2018-11-24","cited_by_count":1}],"next_cursor":null}