Biologically plausible associative memory: Continuous unit response + stochastic dynamics

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. Th...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Segura Meccia, E.C
Otros Autores: Perazzo, Roberto Pedro José
Formato: Capítulo de libro
Lenguaje:Inglés
Publicado: 2002
Acceso en línea:Registro en Scopus
DOI
Handle
Registro en la Biblioteca Digital
Aporte de:Registro referencial: Solicitar el recurso aquí
LEADER 05263caa a22006857a 4500
001 PAPER-20209
003 AR-BaUEN
005 20250819102535.0
008 190411s2002 xx ||||fo|||| 00| 0 eng|d
024 7 |2 scopus  |a 2-s2.0-0036966811 
030 |a NPLEF 
040 |a Scopus  |b spa  |c AR-BaUEN  |d AR-BaUEN 
100 1 |a Segura Meccia, E.C. 
245 1 0 |a Biologically plausible associative memory: Continuous unit response + stochastic dynamics 
260 |c 2002 
270 1 0 |m Segura Meccia, E.C.; Sch. of Computing, Info. Syst. Math., South Bank University, 103 Borough Road, London SE1 0AA, United Kingdom; email: segurae@sbu.ac.uk 
504 |a Amit, D.J., (1989) Modeling Brain Function, , Cambridge University Press, Cambridge 
504 |a Glauber, R.J., Time-dependent statistics of the Ising model (1963) Journal of Mathematical Physics, 4, pp. 294-307 
504 |a 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 
504 |a 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 
504 |a Hopfield, J.J., Neural networks and physical systems with emergent collective computational abilities (1982) Proc. Natl. Acad. Sci., 79, pp. 2554-2558 
504 |a 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 
504 |a Hopfield, J.J., Tank, D.W., Neural' computation of decisions in optimization problems (1985) Biological Cybernetics, 52, pp. 141-152 
504 |a Kampen, N.G.V., (1997) Stochastic Processes in Physics and Chemistry, , Elsevier, Amsterdam 
504 |a Little, W.A., The existence of persistent states in the brain (1974) Mathematical Biosciences, 19, pp. 101-120 
504 |a Little, W.A., Analytic study of the memory storage capacity of a neural network (1978) Mathematical Biosciences, 39, pp. 281-290 
504 |a Peretto, P., Collective properties of neural networks: A statistical physics approach (1984) Biological Cybernetics, 50, pp. 51-62 
504 |a Segura, E.C., Perazzo, R.P.J., Associative memories in infinite dimensional spaces (2000) Neural Processing Letters, 12, pp. 129-144 
506 |2 openaire  |e Política editorial 
520 3 |a 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.  |l eng 
593 |a Sch. of Computing, Info. Syst. Math., South Bank University, 103 Borough Road, London SE1 0AA, United Kingdom 
593 |a Departamento de Fisica, Universidad de Buenos Aires, Ciudad Universitaria, (1428) Buenos Aires, Argentina 
690 1 0 |a ASSOCIATIVE MEMORY 
690 1 0 |a FOKKER-PLANCK EQUATION 
690 1 0 |a GRADED RESPONSE 
690 1 0 |a HOPFIELD MODEL 
690 1 0 |a STOCHASTIC DYNAMICS 
690 1 0 |a ASYMPTOTIC STABILITY 
690 1 0 |a COMPUTER SIMULATION 
690 1 0 |a NEURAL NETWORKS 
690 1 0 |a NUMERICAL METHODS 
690 1 0 |a PROBABILITY DENSITY FUNCTION 
690 1 0 |a PROBABILITY DISTRIBUTIONS 
690 1 0 |a RANDOM PROCESSES 
690 1 0 |a BIOLOGICALLY PLAUSIBLE ASSOCIATIVE MEMORY 
690 1 0 |a CONTINUOUS UNIT RESPONSE 
690 1 0 |a FOKKER-PLANCK EQUATION 
690 1 0 |a GRADED RESPONSE 
690 1 0 |a HOPFIELD MODEL 
690 1 0 |a STOCHASTIC DYNAMICS 
690 1 0 |a ASSOCIATIVE STORAGE 
700 1 |a Perazzo, Roberto Pedro José 
773 0 |d 2002  |g v. 16  |h pp. 243-257  |k n. 3  |p Neural Process Letters  |x 13704621  |t Neural Processing Letters 
856 4 1 |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-0036966811&doi=10.1023%2fA%3a1021742025239&partnerID=40&md5=e576d5c7b7187490751b681fe44871e9  |y Registro en Scopus 
856 4 0 |u https://doi.org/10.1023/A:1021742025239  |y DOI 
856 4 0 |u https://hdl.handle.net/20.500.12110/paper_13704621_v16_n3_p243_SeguraMeccia  |y Handle 
856 4 0 |u https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_13704621_v16_n3_p243_SeguraMeccia  |y Registro en la Biblioteca Digital 
961 |a paper_13704621_v16_n3_p243_SeguraMeccia  |b paper  |c PE 
962 |a info:eu-repo/semantics/article  |a info:ar-repo/semantics/artículo  |b info:eu-repo/semantics/publishedVersion 
999 |c 81162