|  | |||||||||
1
AN INTRODUCTION: ON
SYMBOLIC PROCESSING IN
NEURAL NETWORKS
Ron Sun
Department of Computer Science
College of Engineering
The University of Alabama
Tuscaloosa, AL 35487
1 SOME BACKGROUND
Various forms of life have been existing on earth for hundreds of millions of years, and the long history has seen the development of life from single cell organisms to invertebrates, to vertebrates, and to humans, the truly intelligent beings. The biological organizations of various species, from the lowest to the highest, differ in their complexities and sizes. Such differences in internal complexity manifest in the differences in overt behaviors and intelligence, and generally speaking, organizational complexities of various species are proportionate with capabilities displayed by respective species. However, a gap seems to exist when one goes from high vertebrate animals to humans, in that a conscious, rational capacity is readily available to human beings, that does not seem to be present in any other animals, no matter how high they are on the evolutionary hierarchy. There is a qualitative difference. Yet, strange enough, there is no known qualitative difference between the biological make-up of human brains and animal brains. So the questions are: Where does the difference lie? What is the key to the emergence of rational thinking and intelligence? 1
It is well known that human and animal brains are made up of eural networks", or densely interconnected special kinds of cells, namely neurons, that
1The physical symbol hypothesis attempts to answer this question. However, it is deficient in several respects: it does not answer the question of how intelligent behaviors and their requisite physical symbols (according to the advocates of the theory) emerge from biological systems; it does not take into account subconceptual and intuitive thinking (see Smolensky [22] and Dreyfus & Dreyfus [5]) and does not address the question of how rational thinking can be coupled with such intuitive thinking; it ignores low-level processes (such as pattern recognition) and their interactions with high-level processes (Harnad [11]).
1