AGCS Technique to Improve the Performance of Neural Networks

Author:

Katha Kishor Kumar1,Pabboju Suresh2

Affiliation:

1. Department of Computer Science and Engineering, Osmania University, Hyderabad 500 007, India

2. Department of Information Technology, Chaitanya Bharathi Institute of Technology, Hyderabad 500 075, India

Abstract

Abstract In this paper, a fresh method is offered regarding training of particular neural networks. This technique is a combination of the adaptive genetic (AG) and cuckoo search (CS) algorithms, called the AGCS method. The intention of training a particular artificial neural network (ANN) is to obtain the finest weight load. With this protocol, a particular weight is taken into account as feedback, which is optimized by means of the hybrid AGCS protocol. In the beginning, a collection of weights is initialized and the similar miscalculation is discovered. Finally, during training of an ANN, we can easily overcome the training complications involving ANNs and also gain the finest overall performance with training of the ANN. We have implemented the proposed system in MATLAB, and the overall accuracy is about 93%, which is much better than that of the genetic algorithm (86%) and CS (88%) algorithm.

Publisher

Walter de Gruyter GmbH

Subject

Artificial Intelligence,Information Systems,Software

Reference42 articles.

1. Evolutionary algorithm for optimal connection weights in artificial neural networks;Int. J. Eng.,2011

2. Evolutionary algorithms for reinforcement learning,;J. Artif. Intell. Res.,1999

3. Answer set programming for procedural content generation: a design space approach;IEEE Trans. Comput. Intell. AI Games,2011

4. Artificial neural network co-optimization algorithm based on differential evolution;Proceedings of Second International Symposium on Computational Intelligence and Design,2009

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