The duality of utility and information in optimally learning systems.

Belavkin, Roman V. (2008) The duality of utility and information in optimally learning systems. In: IEEE Systems, Man and Cibernetics Society, UK and Republic of Ireland: 7th conference on cybernetics intelligent systems, 2008., 8th-9th September 2008, Middlesex University, London.

[img]
Preview
PDF
251kB

Official URL: http://www.eis.mdx.ac.uk/staffpages/rvb/publicatio...

Abstract

The paper considers learning systems as optimisation systems with dynamical information constraints, and general optimality conditions are derived using the duality between the space of utility functions and probability measures. The increasing dynamics of the constraints is used to parametrise the optimal solutions which form a trajectory in the space of probability measures. Stochastic processes following such trajectories describe systems achieving the maximum possible utility gain with respect to a given information. The theory is discussed on examples for finite and uncountable sets and in relation to existing applications and cognitive models of learning.

Item Type:Conference or Workshop Item (Paper)
Research Areas:Middlesex University Schools and Centres > School of Science and Technology > Computer Science
Middlesex University Schools and Centres > School of Science and Technology > Computer Science > Artificial Intelligence group
ID Code:3491
Useful Links:
Deposited On:24 Mar 2010 10:31
Last Modified:09 Dec 2014 13:39

Repository staff only: item control page

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year