Associative memories: randomness, continuity and biological plausibility

A new, biologically plausible model of associative memory is presented. First, a historical perspective of the more relevant improvements to the basic Little-Hopfield model is given. Then, we introduce a stochastic system with graded response neurons and a network consisting of a non countable numbe...

Descripción completa

Detalles Bibliográficos
Autor principal: Segura Meccia, Enrique Carlos
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2001
Materias:
Ciencias Informáticas
associative memory
dynamical systems
Hopfieldmodel
Fokker-Planck equation
Neural nets
ARTIFICIAL INTELLIGENCE
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23391
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23391
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
associative memory
dynamical systems
Hopfieldmodel
Fokker-Planck equation
Neural nets
ARTIFICIAL INTELLIGENCE
spellingShingle Ciencias Informáticas
associative memory
dynamical systems
Hopfieldmodel
Fokker-Planck equation
Neural nets
ARTIFICIAL INTELLIGENCE
Segura Meccia, Enrique Carlos
Associative memories: randomness, continuity and biological plausibility
topic_facet Ciencias Informáticas
associative memory
dynamical systems
Hopfieldmodel
Fokker-Planck equation
Neural nets
ARTIFICIAL INTELLIGENCE
description A new, biologically plausible model of associative memory is presented. First, a historical perspective of the more relevant improvements to the basic Little-Hopfield model is given. Then, we introduce a stochastic system with graded response neurons and a network consisting of a non countable number of neurons organized in a continuous metric space. We do this by casting the retrieval process of an analog Hopfield model [7] into the framework of a diffusive process governed by the Fokker-Plank (F-P) equation. This model has the ability to escape spurious memories and, at the same time, is continuous in neural transfer function, topology and time scale. However, it requires the use of path integrals on functional, infinite dimensional spaces, thus turning very difficult any further analytical treatment. Then we resign the continuous topological description of the state space, unifying the graded response units model [7] and the stochastic approach, and obtaining a complete description of the retrieval process at both the microscopic, individual neuron level and the macroscopic level of time evolution of the probability density function over the space of all possible activation patterns.
format Objeto de conferencia
Objeto de conferencia
author Segura Meccia, Enrique Carlos
author_facet Segura Meccia, Enrique Carlos
author_sort Segura Meccia, Enrique Carlos
title Associative memories: randomness, continuity and biological plausibility
title_short Associative memories: randomness, continuity and biological plausibility
title_full Associative memories: randomness, continuity and biological plausibility
title_fullStr Associative memories: randomness, continuity and biological plausibility
title_full_unstemmed Associative memories: randomness, continuity and biological plausibility
title_sort associative memories: randomness, continuity and biological plausibility
publishDate 2001
url http://sedici.unlp.edu.ar/handle/10915/23391
work_keys_str_mv AT seguramecciaenriquecarlos associativememoriesrandomnesscontinuityandbiologicalplausibility
bdutipo_str Repositorios
_version_ 1764820465875943424

Ejemplares similares