Conceptions and Modeling for Transmitted Information Evaluation by ANN

Article type: Research Article

Authors: Garliauskas, Algis

Affiliations: Vilnius Gediminas Technical University & Institute of Mathematics and Informatics, Saulėtekio 11, LT‐2054, Vilnius, Lithuania, e‐mail: [email protected]

Abstract: In this paper, the main measure, an amount of information, of the information theory is analyzed and corrected. The three conceptions of the theory on the microstate, dissipation pathways, and self‐organization levels with a tight connection to the statistical physics are discussed. The concepts of restricted information were introduced as well as the proof of uniqueness of the entropy function, when the probabilities are rational numbers, is presented. The artificial neural network (ANN) model for mapping the evaluation of transmitted information has been designed and experimentally approbated in the biological area.

Keywords: information theory, entropy, amount of information, artificial neural networks

Journal: Informatica, vol. 15, no. 4, pp. 475-488, 2004