Pattern recognition and associative memory as dynamical processes in nonlinear systems
暂无分享，去创建一个
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.<<ETX>>
[1] Haken,et al. Static, wavelike, and chaotic thermal convection in spherical geometries. , 1986, Physical review. A, General physics.
[2] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.
[3] Maureen Caudill,et al. IEEE First International Conference on Neural Networks : Sheraton Harbor Island East, San Diego, California, June 21-24, 1987 , 1987 .