Abstract
There is growing interest in highly interconnected networks of very simple processing elements within artificial intelligence circles. These networks are referred to as connectionist networks and play an increasingly important role in artificial intelligence and cognitive science. This paper attempts to explicate the motivation behind pursuing connectionist networks, and discusses some recent proposals that adopt a connectionist approach to solving problems of visual recognition, knowledge representation, limited inference, and natural language understanding.
© 1987 Optical Society of America
Full Article | PDF ArticleMore Like This
Michael A. Cohen and Stephen Grossberg
Appl. Opt. 26(10) 1866-1891 (1987)
Aloke Guha and M. W. Derstine
Appl. Opt. 29(14) 2187-2200 (1990)
Thomas W. Ryan, C. L. Winter, and Charles J. Turner
Appl. Opt. 26(23) 4961-4971 (1987)