Neural Computation, Vol 8, 390-402, Copyright © 1996 by The MIT Press

ARTICLES

Circular nodes in neural networks

MJ Kirby and R Miranda
Department of Mathematics, Colorado State University, Fort Collins 80523 USA.

In the usual construction of a neural network, the individual nodes store and transmit real numbers that lie in an interval on the real line; the values are often envisioned as amplitudes. In this article we present a design for a circular node, which is capable of storing and transmitting angular information. We develop the forward and backward propagation formulas for a network containing circular nodes. We show how the use of circular nodes may facilitate the characterization and parameterization of periodic phenomena in general. We describe applications to constructing circular self-maps, periodic compression, and one-dimensional manifold decomposition. We show that a circular node may be used to construct a homeomorphism between a trefoil knot in R3 and a unit circle. We give an application with a network that encodes the dynamic system on the limit cycle of the Kuramoto- Sivashinsky equation. This is achieved by incorporating a circular node in the bottleneck layer of a three-hidden-layer bottleneck network architecture. Exploiting circular nodes systematically offers a neural network alternative to Fourier series decomposition in approximating periodic or almost periodic functions.

This article has been cited by other articles:

				M. Scholz, F. Kaplan, C. L. Guy, J. Kopka, and J. Selbig Non-linear PCA: a missing data approach Bioinformatics, October 15, 2005; 21(20): 3887 - 3895. [Abstract] [Full Text] [PDF]