Phase space learning in an autonomous dynamical neural network

In this paper, we present an improved version of the online phase-space learning algorithm of Tsung and Cottrell (1995), called ARTISTE (Autonomous Real-TIme Selection of Training Examples). The new version’s advantages derive from an online adaptive learning rate that depends on the error. We demonstrate the algorithm’s efficacy on two problems: learning a pair of sine waves offset by 901 and the van der Pol oscillator. The online version of the algorithm allows the system to learn as it behaves. We show that the adaptive learning rate technique gives us excellent results in the learning of the above two tasks. Published by Elsevier B.V.