Introduction and Overview

Abstract

This book is about the integration of neural networks and symbolic rules. While symbolic artificial intelligence assumes that the mind is the focus of intelligence, and thus intelligent behaviour emerges from complex symbol processing mechanisms, connectionist artificial intelligence admits that intelligence lies in the brain, and therefore tries to model it by simulating its electrochemical neuronal structures. Clearly, such structures are capable of learning and performing the higher level cognitive tasks that human beings are accustomed to, as well as lower level, everyday cognitive activities. In this framework, the role of symbolic computation is to provide the system with the background information needed for the learning process, as well as to provide us with the information needed for understanding the system, since high-level cognitive tasks are much more clearly digested by human beings as symbols and operations over symbols rather than in the form of interconnected neurons.