Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/30851
Title: | Training neural networks with ant colony optimization algorithms for pattern classification | Authors: | Mavrovouniotis, Michalis Yang, Shengxiang |
Major Field of Science: | Natural Sciences | Field Category: | Computer and Information Sciences | Keywords: | Ant colony optimization;Neural networks;Pattern classification | Issue Date: | 18-Jun-2015 | Source: | Soft Computing, 2015, vol. 19, iss. 6, pp. 1511 - 1522 | Volume: | 19 | Issue: | 6 | Start page: | 1511 | End page: | 1522 | Journal: | Soft Computing | Abstract: | Feed-forward neural networks are commonly used for pattern classification. The classification accuracy of feed-forward neural networks depends on the configuration selected and the training process. Once the architecture of the network is decided, training algorithms, usually gradient descent techniques, are used to determine the connection weights of the feed-forward neural network. However, gradient descent techniques often get trapped in local optima of the search landscape. To address this issue, an ant colony optimization (ACO) algorithm is applied to train feed-forward neural networks for pattern classification in this paper. In addition, the ACO training algorithm is hybridized with gradient descent training. Both standalone and hybrid ACO training algorithms are evaluated on several benchmark pattern classification problems, and compared with other swarm intelligence, evolutionary and traditional training algorithms. The experimental results show the efficiency of the proposed ACO training algorithms for feed-forward neural networks for pattern classification. | URI: | https://hdl.handle.net/20.500.14279/30851 | ISSN: | 14327643 | DOI: | 10.1007/s00500-014-1334-5 | Rights: | © Springer | Type: | Article | Affiliation : | De Montfort University | Publication Type: | Peer Reviewed |
Appears in Collections: | Άρθρα/Articles |
CORE Recommender
SCOPUSTM
Citations
20
79
checked on Mar 14, 2024
Page view(s)
83
Last Week
0
0
Last month
10
10
checked on Aug 30, 2024
Google ScholarTM
Check
Altmetric
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.