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...
| Publicado: |
2002
|
|---|---|
| Materias: | |
| Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_13704621_v16_n3_p243_SeguraMeccia http://hdl.handle.net/20.500.12110/paper_13704621_v16_n3_p243_SeguraMeccia |
| Aporte de: |
| id |
paper:paper_13704621_v16_n3_p243_SeguraMeccia |
|---|---|
| record_format |
dspace |
| spelling |
paper:paper_13704621_v16_n3_p243_SeguraMeccia2023-06-08T16:12:15Z Biologically plausible associative memory: Continuous unit response + stochastic dynamics 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 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. 2002 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_13704621_v16_n3_p243_SeguraMeccia http://hdl.handle.net/20.500.12110/paper_13704621_v16_n3_p243_SeguraMeccia |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
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 |
| spellingShingle |
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 Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
| topic_facet |
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 |
| description |
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. |
| title |
Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
| title_short |
Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
| title_full |
Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
| title_fullStr |
Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
| title_full_unstemmed |
Biologically plausible associative memory: Continuous unit response + stochastic dynamics |
| title_sort |
biologically plausible associative memory: continuous unit response + stochastic dynamics |
| publishDate |
2002 |
| url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_13704621_v16_n3_p243_SeguraMeccia http://hdl.handle.net/20.500.12110/paper_13704621_v16_n3_p243_SeguraMeccia |
| _version_ |
1768545342686494720 |