Connectionist computations of intuitionistic reasoning

A S D Garcez, L C Lamb, D M Gabbay

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

The construction of computational models with provision for effective learning and added reasoning is a fundamental problem in computer science. In this paper, we present a new computational model for integrated reasoning and learning that combines intuitionistic reasoning and neural networks. We use ensembles of neural networks to represent intuitionistic theories, and show that for each intuitionistic theory and intuitionistic modal theory there exists a corresponding neural network ensemble that computes a fixed-point semantics of the theory. This provides a massively parallel model for intuitionistic reasoning. In our model, the neural networks can be trained from examples to adapt to new situations using standard neural learning algorithms, thus providing a unifying foundation for intuitionistic reasoning, knowledge representation, and learning. (C) 2006 Elsevier B.V. All rights reserved
Original languageEnglish
Pages (from-to)34 - 55
Number of pages22
JournalTheoretical Computer Science
Volume358
Issue number1
DOIs
Publication statusPublished - 31 Jul 2006

Fingerprint

Dive into the research topics of 'Connectionist computations of intuitionistic reasoning'. Together they form a unique fingerprint.

Cite this