Continuous learning automata and adaptive digital filter design

Howell, M. N. and Gordon, Timothy (1998) Continuous learning automata and adaptive digital filter design. In: 1998 International Conference on Control, 1-4 September 1998, Swansea, Wales.

Full content URL: http://dx.doi.org/10.1049/cp:19980209

Full text not available from this repository.

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

In the design of adaptive IIR filters, the multi-modal nature of the error surfaces can limit the use of gradient-based and other iterative search methods. Stochastic learning automata have previously been shown to have global optimisation properties making them suitable for the optimisation of filter coefficients. Continuous action reinforcement learning automata are presented as an extension to the standard automata which operate over discrete parameter sets. Global convergence is claimed, and demonstrations are carried out via a number of computer simulations.

Keywords:Automata theory, Convergence of numerical methods, Error detection, IIR filters, Iterative methods, Learning systems, Optimization, Parameter estimation, Random processes, Reinforcement learning automata, Stochastic learning automata, Adaptive filtering
Subjects:H Engineering > H990 Engineering not elsewhere classified
H Engineering > H650 Systems Engineering
Divisions:College of Science > School of Engineering
ID Code:11686
Deposited On:04 Oct 2013 11:55

Repository Staff Only: item control page