Speeding Up Backpropagation Using Multiobjective Evolutionary Algorithms

Author:

Abbass Hussein A.1

Affiliation:

1. Artificial Life and Adaptive Robotics Lab, School of Information Technology and Electrical Engineering, University of New South Wales, Australian Defence Force Academy, Canberra, ACT 2600, Australia,

Abstract

The use of backpropagation for training artificial neural networks (ANNs) is usually associated with a long training process. The user needs to experiment with a number of network architectures; with larger networks, more computational cost in terms of training time is required. The objective of this letter is to present an optimization algorithm, comprising a multiobjective evolutionary algorithm and a gradient-based local search. In the rest of the letter, this is referred to as the memetic Pareto artificial neural network algorithm for training ANNs. The evolutionary approach is used to train the network and simultaneously optimize its architecture. The result is a set of networks, with each network in the set attempting to optimize both the training error and the architecture. We also present a self-adaptive version with lower computational cost. We show empirically that the proposed method is capable of reducing the training time compared to gradient–based techniques.

Publisher

MIT Press - Journals

Subject

Cognitive Neuroscience,Arts and Humanities (miscellaneous)

Cited by 106 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. A Survey on Genetic Fuzzy Systems;Archives of Computational Methods in Engineering;2024-06-27

2. Multiobjective bilevel programming model for multilayer perceptron neural networks;Information Sciences;2023-09

3. Review and assessment of prior work on and future directions for gradient descent-trained expert systems;Disruptive Technologies in Information Sciences VII;2023-06-15

4. Multi-Objective Optimization for Neural Network Structure;2023 28th International Computer Conference, Computer Society of Iran (CSICC);2023-01-25

5. Climate variability impacts on runoff projection under quantile mapping bias correction in the support CMIP6: An investigation in Lushi basin of China;Journal of Hydrology;2022-11

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3