Displaying 21 – 40 of 84

Showing per page

The entropy of Łukasiewicz-languages

Ludwig Staiger (2005)

RAIRO - Theoretical Informatics and Applications - Informatique Théorique et Applications

The paper presents an elementary approach for the calculation of the entropy of a class of languages. This approach is based on the consideration of roots of a real polynomial and is also suitable for calculating the Bernoulli measure. The class of languages we consider here is a generalisation of the Łukasiewicz language.

The entropy of Łukasiewicz-languages

Ludwig Staiger (2010)

RAIRO - Theoretical Informatics and Applications

The paper presents an elementary approach for the calculation of the entropy of a class of languages. This approach is based on the consideration of roots of a real polynomial and is also suitable for calculating the Bernoulli measure. The class of languages we consider here is a generalisation of the Łukasiewicz language.

The irrelevant information principle for collective probabilistic reasoning

Martin Adamčík, George Wilmers (2014)

Kybernetika

Within the framework of discrete probabilistic uncertain reasoning a large literature exists justifying the maximum entropy inference process, error , as being optimal in the context of a single agent whose subjective probabilistic knowledge base is consistent. In particular Paris and Vencovská completely characterised the error inference process by means of an attractive set of axioms which an inference process should satisfy. More recently the second author extended the Paris-Vencovská axiomatic approach...

The logic of neural networks.

Juan Luis Castro, Enric Trillas (1998)

Mathware and Soft Computing

This paper establishes the equivalence between multilayer feedforward networks and linear combinations of Lukasiewicz propositions. In this sense, multilayer forward networks have a logic interpretation, which should permit to apply logical techniques in the neural networks framework.

Currently displaying 21 – 40 of 84