Rotor Neurons — Formalism and Dynamics

Research output: Contribution to journalArticle

Standard

Rotor Neurons — Formalism and Dynamics. / Gislén, Lars; Peterson, Carsten; Söderberg, Bo.

In: Neural Computation, Vol. 4, No. 5, 1992, p. 737-745.

Research output: Contribution to journalArticle

Harvard

APA

CBE

MLA

Vancouver

Author

Gislén, Lars ; Peterson, Carsten ; Söderberg, Bo. / Rotor Neurons — Formalism and Dynamics. In: Neural Computation. 1992 ; Vol. 4, No. 5. pp. 737-745.

RIS

TY - JOUR

T1 - Rotor Neurons — Formalism and Dynamics

AU - Gislén, Lars

AU - Peterson, Carsten

AU - Söderberg, Bo

PY - 1992

Y1 - 1992

N2 - 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 illustrated with 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.

AB - 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 illustrated with 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.

U2 - 10.1162/neco.1992.4.5.737

DO - 10.1162/neco.1992.4.5.737

M3 - Article

VL - 4

SP - 737

EP - 745

JO - Neural Computation

JF - Neural Computation

SN - 1530-888X

IS - 5

ER -