FONN: Combining First Order Logic with Connectionist Learning

Abstract

This paper presents a neural network architecture that can manage structured data and refine knowledge bases expressed in a first order logic language. The presented framework is well suited to classification problems in which concept descriptions depend upon numerical features of the data. In fact, the main goal of the neural architecture is that of refining the numerical part of the knowledge base, without changing its structure. In particular, we discuss a method to translate a set of classification rules into neural computation units. Here, we focus our attention on the translation method and on algorithms to refine network weights on structured data. The classification theory to be refined can be manually handcrafted or automatically acquired by a symbolic relational learning system able to deal with numerical features. As a matter of fact, the primary goal is to bring into a neural network architecture the capability of dealing with structured data of unrestricted size, by allowi...