On a semantics for neural networks based on fuzzy quantifiers
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The concept of a fuzzy linguistic quantifier is introduced and the process for determining the truth of propositions containing linguistic quantifiers, and how this truth value can be viewed as the firing level of an artificial neuron is shown.
Abstract
We describe the aggregation process of the typical artificial neuron. We introduce the concept of a fuzzy linguistic quantifier and describe the process for determining the truth of propositions containing linguistic quantifiers. We show how this truth value can be viewed as the firing level of an artificial neuron. We show the relationship between fuzzy sets and neural inputs. A new class of neurons called owa-neurons is described. A learning algorithm for this class of neurons is presented. We provide a methodology for processing information in non-numeric neural networks. © 1992 John Wiley & Sons, Inc.