ROTOR NEURONS - BASIC FORMALISM AND DYNAMICS
Lars Gisl\'{e}n, Carsten Peterson and Bo S\"{o}derberg
Abstract: Rotor neurons are introduced to encode states living on the surface of a
sphere in D dimensions. Such rotors can be regarded as continuous generalizations
of binary (Ising) neurons. The corresponding mean field equations are derived, and
phase transition properties based on linearized dynamics are given. The power of
this approach is illustratedwith an optimization problem -- placing N identical
charges on a sphere such that the overall repulsive energy is minimized. The rotor
approach appears superior to other methods for this problem both with respect to
solution quality and computational effort needed.
LU TP 91-21