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...
Guardado en:
| Autor principal: | |
|---|---|
| Otros Autores: | |
| 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 | ||