Morphological Rules of Similarity for Hierarchical Distributed Representations

Joel de L. Pereira Castro Jr.

This paper presents and discusses four new criteria that are able to correctly identify hierarchical relationships (in top-down and bottom-up fashion) created upon binary distributed representations. Each criterion is mathematically formulated in terms of two separate rules of similarity, each one being able to identify one type of hierarchical relationship (either top-down or bottom-up). The rules are also presented in terms of a given frame of reference in accordance with the hierarchical distributed representations. Several mathematical correspondences are shown among different criteria and the rules that compose them. It is proven that the new rules used to identify hierarchical relationships between two patterns represent the mathematical decomposition of the hamming distance among them. The combination of the rules able to identify one type of hierarchical relationship can be used to identify particular cluster of patterns with special meaning. This diminishes the need of defining state spaces with high-dimensionality.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: