Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Pruning Deep Convolutional Neural Networks Architectures with Evolution Strategy

Full text
Author(s):
Fernandes, Jr., Francisco E. [1, 2] ; Yen, Gary G. [3]
Total Authors: 2
Affiliation:
[1] Oklahoma State Univ, Stillwater, OK 74078 - USA
[2] Univ Sao Paulo, Inst Math Sci & Comp, BR-13566590 Sao Carlos, SP - Brazil
[3] Oklahoma State Univ, Sch Elect & Comp Engn, Stillwater, OK 74078 - USA
Total Affiliations: 3
Document type: Journal article
Source: INFORMATION SCIENCES; v. 552, p. 29-47, APR 2021.
Web of Science Citations: 5
Abstract

Currently, Deep Convolutional Neural Networks (DCNNs) are used to solve all kinds of problems in the field of machine learning and artificial intelligence due to their learning and adaptation capabilities. However, most successful DCNN models have a high computational complexity making them difficult to deploy on mobile or embedded platforms. This problem has prompted many researchers to develop algorithms and approaches to help reduce the computational complexity of such models. One of them is called filter pruning, where convolution filters are eliminated to reduce the number of parameters and, consequently, the computational complexity of the given model. In the present work, we propose a novel algorithm to perform filter pruning by using a Multi-Objective Evolution Strategy (MOES) algorithm, called DeepPruningES. Our approach avoids the need for using any knowledge during the pruning procedure and helps decision-makers by returning three pruned CNN models with different trade-offs between performance and computational complexity. We show that DeepPruningES can significantly reduce a model's computational complexity by testing it on three DCNN architectures: Convolutional Neural Networks (CNNs), Residual Neural Networks (ResNets), and Densely Connected Neural Networks (DenseNets). (C) 2020 Elsevier Inc. All rights reserved. (AU)

FAPESP's process: 20/05426-0 - Image processing for flood detection and prediction
Grantee:Francisco Erivaldo Fernandes Junior
Support Opportunities: Scholarships in Brazil - Post-Doctoral