Pruning deep neural networks for green energy-efficient models: A survey

J Tmamna, EB Ayed, R Fourati, M Gogate, T Arslan… - Cognitive …, 2024 - Springer
Over the past few years, larger and deeper neural network models, particularly convolutional
neural networks (CNNs), have consistently advanced state-of-the-art performance across …

Literature review of deep network compression

A Alqahtani, X **e, MW Jones - Informatics, 2021 - mdpi.com
Deep networks often possess a vast number of parameters, and their significant redundancy
in parameterization has become a widely-recognized property. This presents significant …

[HTML][HTML] Pruning by explaining: A novel criterion for deep neural network pruning

SK Yeom, P Seegerer, S Lapuschkin, A Binder… - Pattern Recognition, 2021 - Elsevier
The success of convolutional neural networks (CNNs) in various applications is
accompanied by a significant increase in computation and parameter storage costs. Recent …

Automatic network pruning via hilbert-schmidt independence criterion lasso under information bottleneck principle

S Guo, L Zhang, X Zheng, Y Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Most existing neural network pruning methods hand-crafted their importance criteria and
structures to prune. This constructs heavy and unintended dependencies on heuristics and …

Automatic sparse connectivity learning for neural networks

Z Tang, L Luo, B **e, Y Zhu, R Zhao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Since sparse neural networks usually contain many zero weights, these unnecessary
network connections can potentially be eliminated without degrading network performance …

LwMLA-NET: A lightweight multi-level attention-based NETwork for segmentation of COVID-19 lungs abnormalities from CT images

K Roy, D Banik, D Bhattacharjee… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
COronaVIrus Disease 2019 (COVID-19) emerged as a global pandemic in the last two
years. Typical abnormal findings in chest computed tomography (CT) images of COVID-19 …

Network pruning using sparse learning and genetic algorithm

Z Wang, F Li, G Shi, X **e, F Wang - Neurocomputing, 2020 - Elsevier
In recent years, convolutional neural networks (CNNs) have achieved success in the field of
computer vision. However, their large storage requirements and high computational …

Lightweight deep neural networks for ship target detection in SAR imagery

J Wang, Z Cui, T Jiang, C Cao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In recent years, deep convolutional neural networks (DCNNs) have been widely used in the
task of ship target detection in synthetic aperture radar (SAR) imagery. However, the vast …

Filter pruning with a feature map entropy importance criterion for convolution neural networks compressing

J Wang, T Jiang, Z Cui, Z Cao - Neurocomputing, 2021 - Elsevier
Abstract Deep Neural Networks (DNN) has made significant progress in recent years.
However, its high computing and storage costs make it challenging to apply on resource …

Relevance-based channel selection in motor imagery brain–computer interface

A Nagarajan, N Robinson, C Guan - Journal of Neural …, 2023 - iopscience.iop.org
Objective. Channel selection in the electroencephalogram (EEG)-based brain–computer
interface (BCI) has been extensively studied for over two decades, with the goal being to …