Cloning composition and logical inferences in neural networks using variable-free logic

Autor(en): Gust, H.
Kühnberger, K.-U. 
Stichwörter: Algebraic systems; Cloning composition; Logical inferences, Algebra; Backpropagation; Formal logic; Knowledge representation, Neural networks
Erscheinungsdatum: 2004
Enthalten in: AAAI Fall Symposium - Technical Report
Band: FS-04-03
Startseite: 25
Seitenende: 30
In this paper, we will exemplify compositionality issues of neural networks using logical theories. The idea is to implement first-order logic on the neural level by using category theoretic methods in order to get a variable-free representation of logic with only one operation (composition). More precisely, logic as well as neural networks are represented as algebraic systems. On the underlying algebraic level it is possible to consider compositionality aspects of first-order logical formulas and their realization by a neural network. We will demonstrate the approach with some well-known logical inferences using a straightforward implementation of a simple backpropagation network. Copyright © 2004, American Association for Artificial Intelligence ( All rights reserved.
Conference of 2004 AAAI Fall Symposium ; Conference Date: 21 October 2004 Through 24 October 2004; Conference Code:66627
Externe URL:

Show full item record

Page view(s)

Last Week
Last month
checked on Jun 25, 2024

Google ScholarTM