Exact ART: A complete implementation of an ART network

Author(s): Molenaar, P. | Raijmakers, M. |

Year: 1997

Citation: NEURAL NETWORKS Volume: 10 Issue: 4 Pages: 649-669

Abstract: In this article we introduce a continuous time implementation of adaptive resonance theory (ART). ART designed by Grossberg concerns neural networks that self-organize stable pattern recognition categories of arbitrary sequences of input patterns. In contrast to the current implementations of ART we introduce a complete implementation of an ART network, including all regulatory and logical functions, as a system of ordinary differential equations capable of stand-alone running in real time. This means that transient behavior is kept in tact. This implementation of ART is based on ART 2 and is called Exact ART. Exact ART includes an implementation of a gated dipole field and an implementation of the orienting sub-system. The most important features of Exact ART, which are the design principles of ART 2, are proven mathematically. Also simulation studies show that Exact ART self-organizes stable recognition codes that agree with the classification behavior of ART 2.

Topics: Machine Learning, Models: ART 2 / Fuzzy ART, Modified ART,

PDF download




Cross References