The Gap between Symbol and Non-symbol Processing

Abstract

The gap between symbol processing and non-symbol processing is investigated. Predicate logic and neural network were selected as the typical symbol and non-symbol processing respectively. An intermediate form was introduced to represent both of them in the same framework. Using this intermediate form the characteristics of these two methods of representation and processing are analyzed and compared. Then the syntax of predicate logic is expanded in order to reduce this gap. A way of applying this extended logic to database in order to represent it in a few predicate formulae is discussed.