首页 | 本学科首页   官方微博 | 高级检索  
     


Evolutionary learning with a neuromolecular architecture: a biologically motivated approach to computational adaptability
Authors:Jong-Chen Chen  Michael Conrad
Affiliation:(1) Department of Management Information Systems National YunLin Institute of Technology Touliu, Taiwan, R.O.C. e-mail: jcchen@mis.yuntech.edu.tw, TW;(2) Department of Computer Science Wayne State University, Detroit, Michigan 48202 USA e-mail: conrad@cs.wayne.edu, US
Abstract: The effectiveness of evolutionary learning depends both on the variation-selection search operations used and on the structure-function relations of the organization to which these operations are applied. Some organizations—in particular those that occur in biology—are more evolution friendly than others. We describe an artificial neuromolecular (ANM) architecture that illustrates the structure-function relationships that underlie evolutionary adaptability and the manner in which these relationships can be represented in computer programs. The ANM system, a brain-like design that combines intra- and interneuronal levels of processing, can be coupled to a variety of pattern recognition-effector control tasks. The capabilities of the model, in particular its adaptability properties, are here illustrated in the context of Chinese character recognition.
Keywords:  evolutionary computation  molecular computing  neural computing  Chinese character recognition  adaptability
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号