Abstract:
A neural network model of associative memory is presented which unifies the two historically more relevant enhancements to the basic Little-Hopfield discrete model: the graded response units approach and the stochastic, Glauber-inspired model with a random field representing thermal fluctuations. This is done by casting the retrieval process of the model with graded response neurons, into the framework of a diffusive process governed by the Fokker-Plank equation, which leads to a Langevin system describing the process at a microscopic level, while the time evolution of the probability density function is governed by a multivariate Fokker Planck equation operating over the space of all possible activation patterns. The present unified approach has two notable features: (i) greater biological plausibility and (ii) ability to escape local minima of energy (associated with spurious memories), which makes it a potential tool for those complex optimization problems for which the previous models failed.
Registro:
Documento: |
Artículo
|
Título: | Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
Autor: | Segura Meccia, E.C.; Perazzo, R.P.J. |
Filiación: | Sch. of Computing, Info. Syst. Math., South Bank University, 103 Borough Road, London SE1 0AA, United Kingdom Departamento de Fisica, Universidad de Buenos Aires, Ciudad Universitaria, (1428) Buenos Aires, Argentina
|
Palabras clave: | Associative memory; Fokker-Planck equation; Graded response; Hopfield model; Stochastic dynamics; Asymptotic stability; Computer simulation; Neural networks; Numerical methods; Probability density function; Probability distributions; Random processes; Biologically plausible associative memory; Continuous unit response; Fokker-Planck equation; Graded response; Hopfield model; Stochastic dynamics; Associative storage |
Año: | 2002
|
Volumen: | 16
|
Número: | 3
|
Página de inicio: | 243
|
Página de fin: | 257
|
DOI: |
http://dx.doi.org/10.1023/A:1021742025239 |
Título revista: | Neural Processing Letters
|
Título revista abreviado: | Neural Process Letters
|
ISSN: | 13704621
|
CODEN: | NPLEF
|
Registro: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_13704621_v16_n3_p243_SeguraMeccia |
Referencias:
- Amit, D.J., (1989) Modeling Brain Function, , Cambridge University Press, Cambridge
- Glauber, R.J., Time-dependent statistics of the Ising model (1963) Journal of Mathematical Physics, 4, pp. 294-307
- Hartman, E.J., Keeler, J.D., Kowalsky, J.M., Layered neural networks with Gaussian hidden units as universal approximations Neural Computation, 2, pp. 210-215
- Hinton, G.E., Sejnowsky, T.J., Optimal perceptual inference (1983) Proc. IEEE Conf. Comp. Vision and Patt. Recognition, pp. 448-453. , (Washington, 1983) New York, IEEE
- 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
- Hopfield, J.J., Tank, D.W., Neural' computation of decisions in optimization problems (1985) Biological Cybernetics, 52, pp. 141-152
- Kampen, N.G.V., (1997) Stochastic Processes in Physics and Chemistry, , Elsevier, Amsterdam
- Little, W.A., The existence of persistent states in the brain (1974) Mathematical Biosciences, 19, pp. 101-120
- Little, W.A., Analytic study of the memory storage capacity of a neural network (1978) Mathematical Biosciences, 39, pp. 281-290
- Peretto, P., Collective properties of neural networks: A statistical physics approach (1984) Biological Cybernetics, 50, pp. 51-62
- Segura, E.C., Perazzo, R.P.J., Associative memories in infinite dimensional spaces (2000) Neural Processing Letters, 12, pp. 129-144
Citas:
---------- APA ----------
Segura Meccia, E.C. & Perazzo, R.P.J.
(2002)
. Biologically plausible associative memory: Continuous unit response + stochastic dynamics. Neural Processing Letters, 16(3), 243-257.
http://dx.doi.org/10.1023/A:1021742025239---------- CHICAGO ----------
Segura Meccia, E.C., Perazzo, R.P.J.
"Biologically plausible associative memory: Continuous unit response + stochastic dynamics"
. Neural Processing Letters 16, no. 3
(2002) : 243-257.
http://dx.doi.org/10.1023/A:1021742025239---------- MLA ----------
Segura Meccia, E.C., Perazzo, R.P.J.
"Biologically plausible associative memory: Continuous unit response + stochastic dynamics"
. Neural Processing Letters, vol. 16, no. 3, 2002, pp. 243-257.
http://dx.doi.org/10.1023/A:1021742025239---------- VANCOUVER ----------
Segura Meccia, E.C., Perazzo, R.P.J. Biologically plausible associative memory: Continuous unit response + stochastic dynamics. Neural Process Letters. 2002;16(3):243-257.
http://dx.doi.org/10.1023/A:1021742025239