Results 21 to 30 of about 14,609 (251)
A statistical approach for neural network pruning with application to internet of things
EURASIP Journal on Wireless Communications and Networking, 2023 Pruning is showing huge potential for compressing and accelerating deep neural networks by eliminating redundant parameters. Along with more terminal chips integrated with AI accelerators for internet of things (IoT) devices, structured pruning is ...
Chengchen Mao +3 more
doaj +1 more source
CoRR, 2020 Pruning has become a very powerful and effective technique to compress and accelerate modern neural networks. Existing pruning methods can be grouped into two categories: filter pruning (FP) and weight pruning (WP). FP wins at hardware compatibility but loses at the compression ratio compared with WP.
Fanxu Meng 0003 +6 more
openaire +3 more sources
Dependency Aware Filter Pruning
CoRR, 2020 Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimportant filters is an efficient way to mitigate the inference cost. For this purpose, identifying unimportant convolutional filters is the key to effective filter pruning ...
Kai Zhao 0012 +3 more
openaire +2 more sources
IEEE Access, 2023 In recent years, kernel pruning, which offers the advantages of both weight and filter pruning methods, has been actively conducted. Although kernel pruning must be implemented as structured pruning to obtain the actual network acceleration effect on ...
Kwanghyun Koo, Hyun Kim
doaj +1 more source
Functionality-Oriented Convolutional Filter Pruning [PDF]
CoRR, 2018 The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction.
Zhuwei Qin +3 more
openaire +3 more sources
IEEE Access, 2021 Various pruning methods have been proposed to solve the overparameterized problem in deep neural networks. Most of the structured pruning methods have used magnitude-based filter importance to remove unnecessary filters.
Incheon Cho +3 more
doaj +1 more source
Play and Prune: Adaptive Filter Pruning for Deep Model Compression [PDF]
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019 While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as computational overheads. Consequently, there is a growing need for filter-level pruning approaches for compressing
Pravendra Singh +3 more
openaire +3 more sources
Filter Pruning and Re-Initialization via Latent Space Clustering
IEEE Access, 2020 Filter pruning is prevalent for pruning-based model compression. Most filter pruning methods have two main issues: 1) the pruned network capability depends on that of source pretrained models, and 2) they do not consider that filter weights follow a ...
Seunghyun Lee +3 more
doaj +1 more source
Network Pruning Using Adaptive Exemplar Filters [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2022 Popular network pruning algorithms reduce redundant information by optimizing hand-crafted models, and may cause suboptimal performance and long time in selecting filters. We innovatively introduce adaptive exemplar filters to simplify the algorithm design, resulting in an automatic and efficient pruning approach called EPruner.
Mingbao Lin +6 more
openaire +3 more sources
IEEE Access, 2023 Currently, the use of robots has altered the way people live and their lifestyles. To realize a human-computer interaction system based on robots’ comprehension of human emotions, this study chooses facial expressions as the research object and ...
Jing Pu, Xinxin Nie
doaj +1 more source