Rotor Neurons — Formalism and Dynamics

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

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.

Detaljer

Författare
Enheter & grupper
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Beräkningsmatematik
Originalspråkengelska
Sidor (från-till)737-745
Antal sidor9
TidskriftNeural Computation
Volym4
Utgåva nummer5
StatusPublished - 1992
PublikationskategoriForskning
Peer review utfördJa