Pattern recognition and associative memory as dynamical processes in nonlinear systems
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The authors present a formalism for associative memory and pattern recognition performed by the time evolution of a dynamical system. The patterns are treated as multicomponent vectors, as well as continuous functions in space and time. Equations of motion are derived from a nonlinear potential and transformed to a low-dimensional subspace, where an appropriate form for neural nets is given. The example of rotated patterns shows how the formalism works in that case.Keywords
This publication has 4 references indexed in Scilit:
- Computational Systems — Natural and ArtificialPublished by Springer Nature ,1987
- Static, wavelike, and chaotic thermal convection in spherical geometriesPhysical Review A, 1986
- SynergeticsPublished by Springer Nature ,1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982