【作者】 曹文明； 王建华； 王守觉；

【Author】 Cao Wenming~1 Wang Jianhua~2 Wang Shuojue~3 (1 ATR National Key Laboratory of Defense Technology,Shenzhen University,Guangdong 518060,China;2 Institute of Intelligent Information System,Information College Zhejiang University of Technology,Hangzhou 310034;3 Lab of Artificial Neural Networks.Institute of Semiconductors,CAS,Beijing 100083,China)

【机构】 深圳大学智能信息系统研究所； 浙江工业大学信息工程学院； 中国科学院半导体研究所；

【摘要】 人工神经网络是由大量简单处理单元构成的非线性动力学系统,具有分布式的信息存贮、大规模并行处理、自学习和自组织等特点,可以解决传统计算机难以解决或无法解决的人工智能方面问题。本文结合两者特点,结合符号主义和连接主义两者的特点,提出并实现了一种脱机工作可训练的模式识别专用神经网络系统的结构设计。实验通过一次采样,便可独立完成包括模式采集、特征提取、样本学习以及识别等一整套与实物识别系统,并验证该神经计算机具有合理性。更多还原

【Abstract】 Artificial neural networks are nonlinear dynamic systems which are constituted of abundant sim- ple processing unites,their characteristics include parallel computing,memory distributing,self-learning and self-organization,etc.They are used to solve many artificial intelligence problems that are very difficult or impossible to be solved by traditional computer.Combining the strongpoint of symbolism and connec- tism,a no host learnable special-purpose neural networks for pattern recognition has been proposed in this paper.The no host learnable neural special-purpose networks for pattern recognition is able to capture im- age,extract character,learn and recognition object independently without host.This system including hardware component,programming environment and principal functional modules is introduced in detail.更多还原