Abstract:
A generalization of the Little-Hopfield neural network model for associative memories is presented that considers the case of a continuum of processing units. The state space corresponds to an infinite dimensional euclidean space. A dynamics is proposed that minimizes an energy functional that is a natural extension of the discrete case. The case in which the synaptic weight operator is defined through the autocorrelation rule (Hebb rule) with orthogonal memories is analyzed. We also consider the case of memories that are not orthogonal. Finally, we discuss the generalization of the non deterministic, finite temperature dynamics.
Registro:
Documento: |
Artículo
|
Título: | Associative memories in infinite dimensional spaces |
Autor: | Segura, E.C.; Perazzo, R.P.J. |
Filiación: | Departamento de Computacion, Universidad de Buenos Aires, Pabellon I Ciudad Universitaria, Buenos Aires, 1428, Argentina Centro de Estudios Avanzados, Universidad de Buenos Aires, Argentina
|
Palabras clave: | Associative storage; Correlation methods; State space methods; Autocorrelation; Glauber dynamics; Hopfield models; Infinite dimensional euclidean space; Neural networks |
Año: | 2000
|
Volumen: | 12
|
Número: | 2
|
Página de inicio: | 129
|
Página de fin: | 144
|
DOI: |
http://dx.doi.org/10.1023/A:1009689025427 |
Título revista: | Neural Processing Letters
|
Título revista abreviado: | Neural Process Letters
|
ISSN: | 13704621
|
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_13704621_v12_n2_p129_Segura |
Referencias:
- Little, W.A., The existence of persistent states in the brain (1974) Math. Biosci., 19, pp. 101-120
- Little, W.A., Analytic study of the memory storage capacity of a neural network (1978) Math. Biosci., 39, pp. 281-290
- Hebb, D.O., (1949) The Organization of Behavior: A Neuropsychological Theory, , New York, Wiley
- Amit, D.J., (1989) Modeling Brain Function, , Cambridge, Cambridge University Press
- Hopfield, J.J., Neural networks and physical systems with emergent collective computational abilities (1982) Proc. Natl. Acad. Sci., 79, pp. 2554-2558
- Hopfield, J.J., Neurons with graded response have collective computational properties like those of two-state neurons (1984) Proc. Natl. Acad. Sci., 81, pp. 3088-3092
- Feynman, R.P., Hibbs, A.R., (1965) Quantum Mechanics and Path Integrals, , New York, McGraw-Hill
- Fodor, J.A., (1983) The Modularity of Mind, , Cambridge, MIT Press
- Van Kampen, N.G., (1997) Stochastic Processes in Physics and Chemistry, , Amsterdam, Elsevier
- Hinton, G.E., Sejnowsky, T.J., Optimal perceptual inference (1983) Proc. IEEE Conf. Computer Vision and Pattern Recognition (Washington, 1983), pp. 448-453. , New York, IEEE
- Peretto, P., Collective properties of neural networks: A statistical physics approach Biological Cybernetics, 50, pp. 51-62
- Glauber, R.J., Time dependent statistics of the Ising model (1963) J. of Math. Phys., 4, pp. 294-307
Citas:
---------- APA ----------
Segura, E.C. & Perazzo, R.P.J.
(2000)
. Associative memories in infinite dimensional spaces. Neural Processing Letters, 12(2), 129-144.
http://dx.doi.org/10.1023/A:1009689025427---------- CHICAGO ----------
Segura, E.C., Perazzo, R.P.J.
"Associative memories in infinite dimensional spaces"
. Neural Processing Letters 12, no. 2
(2000) : 129-144.
http://dx.doi.org/10.1023/A:1009689025427---------- MLA ----------
Segura, E.C., Perazzo, R.P.J.
"Associative memories in infinite dimensional spaces"
. Neural Processing Letters, vol. 12, no. 2, 2000, pp. 129-144.
http://dx.doi.org/10.1023/A:1009689025427---------- VANCOUVER ----------
Segura, E.C., Perazzo, R.P.J. Associative memories in infinite dimensional spaces. Neural Process Letters. 2000;12(2):129-144.
http://dx.doi.org/10.1023/A:1009689025427