Class-Wise Classifier Design Capable of Continual Learning Using Adaptive Resonance Theory-Based Topological Clustering

Author:

Masuyama Naoki1ORCID,Nojima Yusuke1ORCID,Dawood Farhan2ORCID,Liu Zongying3ORCID

Affiliation:

1. Graduate School of Informatics, Osaka Metropolitan University, Osaka 599-8531, Japan

2. Faculty of Information Technology, University of Central Punjab, Lahore 54000, Pakistan

3. Faculty of Navigation, Dalian Maritime University, Dalian 116026, China

Abstract

This paper proposes a supervised classification algorithm capable of continual learning by utilizing an Adaptive Resonance Theory (ART)-based growing self-organizing clustering algorithm. The ART-based clustering algorithm is theoretically capable of continual learning, and the proposed algorithm independently applies it to each class of training data for generating classifiers. Whenever an additional training data set from a new class is given, a new ART-based clustering will be defined in a different learning space. Thanks to the above-mentioned features, the proposed algorithm realizes continual learning capability. Simulation experiments showed that the proposed algorithm has superior classification performance compared with state-of-the-art clustering-based classification algorithms capable of continual learning.

Funder

Japan Society for the Promotion of Science (JSPS) KAKENHI

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Reference55 articles.

1. Catastrophic interference in connectionist networks: The sequential learning problem;McCloskey;Psychol. Learn. Motiv.,1989

2. Continual lifelong learning with neural networks: A review;Parisi;Neural Netw.,2019

3. Van de Ven, G.M., and Tolias, A.S. (2019). Three scenarios for continual learning. arXiv.

4. Wiewel, F., and Yang, B. (2019). Localizing catastrophic forgetting in neural networks. arXiv.

5. Overcoming catastrophic forgetting in neural networks;Kirkpatrick;Proc. Natl. Acad. Sci. USA,2017

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