Deterministic learning and rapid dynamical pattern recognition
| Authors: | Wang Cong, South China University of Technology, China
Hill David, The Australian National University, Australia |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Intelligent Modelling and Identification I |
|---|
| Keywords: | Dynamical pattern recognition, deterministic learning, persistent excitation (PE) condition, recognition by synchronization |
|---|
Abstract
Recognition of temporal/dynamical patterns is among the most difficult pattern recognition tasks. In this paper, based on a recent result on deterministic learning theory, a unified framework is proposed for rapid recognition of dynamical patterns. Firstly, it is shown that time-varying dynamical patterns can be effectively represented through deterministic learning. Then, by characterizing the similarity of dynamical patterns based on system dynamics, a dynamical recognition mechanism is proposed. Rapid recognition of dynamical patterns can be implemented when state synchronization is achieved according to a kind of indirect and dynamical matching on system dynamics. The synchronization errors can be taken as the measure of similarity between the test and training patterns.
