Results 231 to 240 of about 6,914,944 (265)

Bearing Remaining Useful Life Prediction Using Federated Learning With Taylor-Expansion Network Pruning

IEEE Transactions on Instrumentation and Measurement, 2023
Accurate prediction of bearing remaining useful life (RUL) is essential for machine health management. In existing data-driven prognostic methods, centralized data resources and deep neural networks (DNNs) are two requisites.
Xi Chen, Haibo Wang, Siliang Lu, Ruqiang Yan   +3 more
semanticscholar   +1 more source

RGP: Neural Network Pruning Through Regular Graph With Edges Swapping

IEEE Transactions on Neural Networks and Learning Systems, 2023
Deep learning technology has found a promising application in lightweight model design, for which pruning is an effective means of achieving a large reduction in both model parameters and float points operations (FLOPs).
Zhuangzhi Chen, Jingyang Xiang, Yao Lu, Qi Xuan, Zhen Wang, Guanrong Chen, Xiaoniu Yang   +6 more
semanticscholar   +1 more source

Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle

IEEE International Conference on Computer Vision, 2023
Most existing neural network pruning methods hand-crafted their importance criteria and structures to prune. This constructs heavy and unintended dependencies on heuristics and expert experience for both the objective and the parameters of the pruning ...
Song Guo, Lei Zhang, Xiawu Zheng, Yan Wang, Yuchao Li, Fei Chao, Chenglin Wu, Shengchuan Zhang, Rongrong Ji   +8 more
semanticscholar   +1 more source

Towards performance-maximizing neural network pruning via global channel attention

Neural Networks, 2023
Network pruning has attracted increasing attention recently for its capability of transferring large-scale neural networks (e.g., CNNs) into resource-constrained devices.
Yingchun Wang, Song Guo, Jingcai Guo, Jiewei Zhang, Weizhan Zhang, Caixia Yan, Yuanhong Zhang   +6 more
semanticscholar   +1 more source

Structural Alignment for Network Pruning through Partial Regularization

IEEE International Conference on Computer Vision, 2023
In this paper, we propose a novel channel pruning method to reduce the computational and storage costs of Convolutional Neural Networks (CNNs). Many existing one-shot pruning methods directly remove redundant structures, which brings a huge gap between ...
Shangqian Gao, Zeyu Zhang, Yanfu Zhang, Feihu Huang, Heng Huang   +4 more
semanticscholar   +1 more source

Brain-Inspired Interpretable Network Pruning for Smart Vision-Based Defect Detection Equipment

IEEE Transactions on Industrial Informatics, 2023
Detection algorithms play an important role in the life-cycle management of smart vision-based defect detection equipment. This article proposes a brain-inspired interpretable network pruning method for smart detection equipment for online defect ...
Junliang Wang, Shuxuan Zhao, Chuqiao Xu, Jie Zhang, Ray Y. Zhong   +4 more
semanticscholar   +1 more source

Neural Network Pruning by Gradient Descent

arXiv.org, 2023
The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability.
Zhang Zhang, Ruyi Tao, Jiang Zhang
semanticscholar   +1 more source

Intermittent-Aware Neural Network Pruning

Design Automation Conference, 2023
Deep neural network inference on energy harvesting tiny devices has emerged as a solution for sustainable edge intelligence. However, compact models optimized for continuously-powered systems may become suboptimal when deployed on intermittently-powered ...
Chih-Chia Lin, Chia-Yin Liu, Chih-Hsuan Yen, Tei-Wei Kuo, P. Hsiu   +4 more
semanticscholar   +1 more source

Towards Fairness-aware Adversarial Network Pruning

IEEE International Conference on Computer Vision, 2023
Network pruning aims to compress models while minimizing loss in accuracy. With the increasing focus on bias in AI systems, the bias inheriting or even magnification nature of traditional network pruning methods has raised a new perspective towards ...
Lei Zhang, Zhibo Wang, Xiaowei Dong, Yunhe Feng, Xiaoyi Pang, Zhifei Zhang, Kui Ren   +6 more
semanticscholar   +1 more source

Network Pruning via Performance Maximization

Computer Vision and Pattern Recognition, 2021
Channel pruning is a class of powerful methods for model compression. When pruning a neural network, it's ideal to obtain a sub-network with higher accuracy.
Shangqian Gao, Feihu Huang, Weidong (Tom) Cai, Heng Huang   +3 more
semanticscholar   +1 more source