Computer Model of a "Sense of Humour". II. Realization in Neural Networks

TL;DR

This paper proposes a neural network-based algorithm to model a sense of humour by recognizing polysemantic sequences, utilizing a modified Hopfield network.

Contribution

It introduces a novel approach to simulate a sense of humour through a neural network algorithm capable of linguistic problem-solving.

Findings

Algorithm successfully recognizes polysemantic sequences

Modified Hopfield model enables linguistic processing

Potential application in artificial humour systems

Abstract

The computer realization of a "sense of humour" requires the creation of an algorithm for solving the "linguistic problem", i.e. the problem of recognizing a continuous sequence of polysemantic images. Such algorithm may be realized in the Hopfield model of a neural network after its proper modification.