Robust competitive networks
Physical Review APublished 1 March 1992
M. Schmutz, Wolfgang Banzhaf
Citations14
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
In the search for networks that implement the winner-take-all function dynamically in a robust way, we study in this paper a class of models that includes short-range diffusive interactions. The analysis is based on a combination of numerical simulations and analytic results obtained by the application of field-theoretical methods. An examination of the ground-state properties reveals that the implementation of robust competition in dimensions higher than one requires a nonstandard diffusive interaction of at least fourth order.
Keywords
Biochemistry, Genetics and Molecular BiologyPhysics and Astronomy
Cognitive ScienceConnectionist Models and Their Properties
1,324 Citations1982Jerome A. Feldman, D.H. Ballard
A general connectionist model is introduced and how it might be used in cognitive science is considered, among the issues addressed are: stability and noise-sensitivity, distributed decision-making, time and sequence problems, and the representation of complex concepts.
Springer series in synergeticsSynergetic Computers and Cognition
404 Citations1991Hermann Haken
This monograph aims to present a novel approach to neural nets and thus offers a genuine alternative to the hitherto known neuro-computers, based on the author's discovery of the profound analogy between pattern recognition and pattern formation in open systems far from equilibrium.