摘要
本文从生物视觉辨识的神经生理学角度,构造一个近似于视皮层功能柱型结构的软件组件来对物体特征进行抽取.每个功能柱的计算功能是用有理平方逼近方法,经迭代训练,求出的多变元有理函数来完成的.本文对模式识别、知识获取、表示与应用的认知观点,强调认知心理功能的计算依托和生理基础.
Cells in area TE of the interotemporal cortex of the brain selectively respond to various moderately complex object features, and those that respond to similar features cluster in a columnar region elongated vertical to the cortical surface. So artificial columnar hierarchical architecture are .significant for knowledge representation, pattern recognition and computer vision, which is the result of hint from neuro -vision, physiology and psychology. Based on this physiological foundation, a rational function is constructed to approximate the mathematical function of a TE column among cortical matrix.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
1998年第2期125-132,共8页
Pattern Recognition and Artificial Intelligence
基金
国家智能机研究开发中心
国家高性能计算基金
关键词
生物视觉
有理平方逼近
知识表示
人工智能
Neuro-Vision, Interotemporal Cortex, Rational Least Square Approximation, Object Recognition, Knowledge Representation
