摘要
提出了基于操作条件反射的仿生自主学习方法,设计了操作条件反射自动机(OCM)的认知模型.与原来的学习自动机相比,该模型增加了状态取向单元,利用'反应-强化'的学习机理,来模拟自然界生物的'随机应变性'.设计了OCM的递归学习算法,用于模拟生物的操作条件反射机制,使其具有仿生的自组织功能,包括自学习和自适应功能.通过模拟Skinner鸽子实验和倒立摆平衡控制实验,验证了该模型具有一定的仿生自主学习能力,可用于描述、模拟和设计各种自组织系统.
This paper presents a bionic autonomous learning method based on operant conditioning automata, and designs a cognitive model of Skinner operant conditioning automata. The model adds a unit of behavior propensity to generate learning mechanism of ' reaction-strengthening' , and simulates nature biotic randomly compliance. A recursive learning algorithm is proposed, which is to simulate biotic operant conditioning mechanism and let it have bionic self-organization function including self-learning function and self-adaptive function. Finally, the model is proved to have the bionic self-learning ability and can be used to descript, simulate, and design various self-organizing systems.
出处
《北京工业大学学报》
EI
CAS
CSCD
北大核心
2011年第11期1631-1637,共7页
Journal of Beijing University of Technology
基金
国家自然科学基金资助项目(60774077)
国家'863计划'资助项目(2007AA04Z226)
北京市教委科研计划
北京市自然科学基金重点项目(KZ200810005002)
关键词
操作条件反射自动机
仿生
自主学习
自组织
operant conditioning automata
bionic
autonomic learning
self-organizing