Results 1 to 10 of about 36,322 (258)
Multi‐objective evolutionary optimization for hardware‐aware neural network pruning [PDF]
Fundamental ResearchNeural 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 +4 more
doaj +4 more sources
Lossless Reconstruction of Convolutional Neural Network for Channel-Based Network Pruning [PDF]
Sensors, 2023 Network pruning reduces the number of parameters and computational costs of convolutional neural networks while maintaining high performance. Although existing pruning methods have achieved excellent results, they do not consider reconstruction after ...
Donghyeon Lee, Eunho Lee, Youngbae Hwang
doaj +2 more sources
Pruning-aware Sparse Regularization for Network Pruning
Machine Intelligence Research, 2023 Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks (CNNs) by pruning the filters of less importance to the final output accuracy. To reduce the degradation of performance after pruning, many methods utilize the loss with sparse regularization to produce structured sparsity.
Xu Zhao, Nanfei Jiang
exaly +3 more sources
Filter Sketch for Network Pruning [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2022 We propose a novel network pruning approach by information preserving of pre-trained network weights (filters). Network pruning with the information preserving is formulated as a matrix sketch problem, which is efficiently solved by the off-the-shelf Frequent Direction method.
Rongrong Ji, Yonghong Tian, Qi Tian
exaly +4 more sources
Progressive multi-level distillation learning for pruning network
Complex & Intelligent Systems, 2023 Although the classification method based on the deep neural network has achieved excellent results in classification tasks, it is difficult to apply to real-time scenarios because of high memory footprints and prohibitive inference times.
Ruiqing Wang +9 more
doaj +2 more sources
Pruning by explaining: A novel criterion for deep neural network pruning
Pattern Recognition, 2021 The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the weights of various layers while at the same time aiming to not sacrifice performance.
Simon Wiedemann +2 more
exaly +5 more sources
Weight-Dependent Gates for Network Pruning
IEEE Transactions on Circuits and Systems for Video Technology, 2022 In this paper, a simple yet effective network pruning framework is proposed to simultaneously address the problems of pruning indicator, pruning ratio, and efficiency constraint. This paper argues that the pruning decision should depend on the convolutional weights, and thus proposes novel weight-dependent gates (W-Gates) to learn the information from ...
Zechun Liu, , Xiangyu Zhang
exaly +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 +7 more
doaj +4 more sources
Network pruning via resource reallocation
Pattern Recognition12 pages, 11 figures, 7 ...
Chen Change Loy, Zheng Ma, Yuenan Hou
exaly +3 more sources
Soft Pruning Algorithm Based on Lottery Ticket Hypothesis [PDF]
Jisuanji gongcheng, 2023 The increasing number of neural network layers exponentially increases the network complexity and limits its application scenarios.To solve this problem，this study proposes a soft pruning algorithm based on lottery ticket hypothesis.The pruning network ...
MA Jiaxiang, SONG Xiaoning
doaj +1 more source