Results 1 to 10 of about 22,594 (260)

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   +4 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

Activation-Based Pruning of Neural Networks

Algorithms
We present a novel technique for pruning called activation-based pruning to effectively prune fully connected feedforward neural networks for multi-object classification. Our technique is based on the number of times each neuron is activated during model
Tushar Ganguli, Edwin K. P. Chong
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, Alexander Binder, Sebastian Lapuschkin   +2 more
exaly   +5 more sources

Rethinking Weight Decay for Efficient Neural Network Pruning [PDF]

Journal of Imaging, 2022
Vincent Gripon, Thomas Hannagan, Mathieu Leonardon   +2 more
exaly   +2 more sources

Lossless Reconstruction of Convolutional Neural Network for Channel-Based Network Pruning

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   +3 more sources

Methods for Pruning Deep Neural Networks [PDF]

IEEE Access, 2022
Major revision that includes additional references and a new section for comparison of ...
Sunil Vadera, Salem Ameen
openaire   +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   +1 more source

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