Results 1 to 10 of about 79,349 (126)

Multi‐objective evolutionary optimization for hardware‐aware neural network pruning [PDF]

Fundamental Research
Neural network pruning is a popular approach to reducing the computational complexity of deep neural networks. In recent years, as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics, and as new types of ...
Wenjing Hong, Guiying Li, Shengcai Liu, Peng Yang, Ke Tang   +4 more
doaj   +4 more sources

Crossbar-Aware Neural Network Pruning

IEEE Access, 2018
Crossbar architecture has been widely adopted in neural network accelerators due to the efficient implementations on vector-matrix multiplication operations.
Ling Liang, Lei Deng, Yueling Zeng, Xing Hu, Yu Ji, Xin Ma, Guoqi Li, Yuan Xie   +7 more
doaj   +3 more sources

Evolutionary Multi-Objective One-Shot Filter Pruning for Designing Lightweight Convolutional Neural Network

Sensors, 2021
Deep neural networks have achieved significant development and wide applications for their amazing performance. However, their complex structure, high computation and storage resource limit their applications in mobile or embedding devices such as sensor
Tao Wu, Jiao Shi, Deyun Zhou, Xiaolong Zheng, Na Li   +4 more
doaj   +3 more sources

Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach

Complex & Intelligent Systems, 2023
Neural network pruning offers great prospects for facilitating the deployment of deep neural networks on computational resource limited devices.
Hanjing Cheng, Zidong Wang, Lifeng Ma, Zhihui Wei, Fawaz E. Alsaadi, Xiaohui Liu   +5 more
doaj   +2 more sources

Absorption Pruning of Deep Neural Network for Object Detection in Remote Sensing Imagery

Remote Sensing, 2022
In recent years, deep convolutional neural networks (DCNNs) have been widely used for object detection tasks in remote sensing images. However, the over-parametrization problem of DCNNs hinders their application in resource-constrained remote sensing ...
Jielei Wang, Zongyong Cui, Zhipeng Zang, Xiangjie Meng, Zongjie Cao   +4 more
doaj   +3 more sources

Rethinking Weight Decay for Efficient Neural Network Pruning [PDF]

Journal of Imaging, 2022
Hugo Tessier, Vincent Gripon, Mathieu Léonardon   +2 more
exaly   +2 more sources

Pruning Method for Convolutional Neural Network Models Based on Sparse Regularization [PDF]

Jisuanji gongcheng, 2021
The existing pruning algorithms for Convolutional Neural Network(CNN) models exhibit a low accuracy in evaluating the importance of parameters by relying on their own parameter information, which would easily lead to mispruning and affect the performance
WEI Yue, CHEN Shichao, ZHU Fenghua, XIONG Gang
doaj   +1 more source

Dynamical Conventional Neural Network Channel Pruning by Genetic Wavelet Channel Search for Image Classification

Frontiers in Computational Neuroscience, 2021
Neural network pruning is critical to alleviating the high computational cost of deep neural networks on resource-limited devices. Conventional network pruning methods compress the network based on the hand-crafted rules with a pre-defined pruning ratio (
Lin Chen, Saijun Gong, Xiaoyu Shi, Mingsheng Shang   +3 more
doaj   +1 more source

Structured Pruning Algorithm with Adaptive Threshold Based on Gradient [PDF]

Jisuanji gongcheng, 2022
The network model needs to be compressed to reduce the number of model parameters and calculational cost to ensure the operation of the Deep Neural Network(DNN) model on edge equipment and real-time analysis. However, most existing pruning algorithms are
WANG Guodong, YE Jian, XIE Ying, QIAN Yueliang
doaj   +1 more source

Adaptive Neural Network Structure Optimization Algorithm Based on Dynamic Nodes

Current Issues in Molecular Biology, 2022
Large-scale artificial neural networks have many redundant structures, making the network fall into the issue of local optimization and extended training time.
Miao Wang, Xu Yang, Yunchong Qian, Yunlin Lei, Jian Cai, Ziyi Huan, Xialv Lin, Hao Dong   +7 more
doaj   +1 more source