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
Analog memristive synapse based on topotactic phase transition for high-performance neuromorphic computing and neural network pruning. [PDF]
Sci Adv, 2021 Memristor with topotactic phase transition demonstrates controllable analog switching and implements neural network pruning. Inspired by the human brain, nonvolatile memories (NVMs)–based neuromorphic computing emerges as a promising paradigm to build ...
Mou X +14 more
europepmc +2 more sources
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 +2 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 +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
A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.
Hongrong Cheng +2 more
semanticscholar +1 more source
YOLO Pruning Algorithm Based on Parameter Subspace and Scaling Factor [PDF]
Jisuanji gongcheng, 2021 In order to ensure the normal operation of YOLO network on embedded devices,it is necessary to use pruning algorithm to simplify the filter to reduce the network storage space and the amount of calculation.
YANG Minjie, LIANG Yaling, DU Minghui
doaj +1 more source
Fast as CHITA: Neural Network Pruning with Combinatorial Optimization [PDF]
International Conference on Machine Learning, 2023 The sheer size of modern neural networks makes model serving a serious computational challenge. A popular class of compression techniques overcomes this challenge by pruning or sparsifying the weights of pretrained networks.
Riade Benbaki +6 more
semanticscholar +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
Convolutional Neural Network Pruning with Structural Redundancy Reduction [PDF]
Computer Vision and Pattern Recognition, 2021 Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to achieve compact ...
Z. Wang, Chengcheng Li, Xiangyang Wang
semanticscholar +1 more source