An entropic associative memory

Abstract Natural memories are associative, declarative and distributed, and memory retrieval is a constructive operation. In addition, cues of objects that are not contained in the memory are rejected directly. Symbolic computing memories resemble natural memories in their declarative character, and...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Luis A. Pineda, Gibrán Fuentes, Rafael Morales
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/23c7c74af93a45528faef4a2a9da2700
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:23c7c74af93a45528faef4a2a9da2700
record_format dspace
spelling oai:doaj.org-article:23c7c74af93a45528faef4a2a9da27002021-12-02T11:45:01ZAn entropic associative memory10.1038/s41598-021-86270-72045-2322https://doaj.org/article/23c7c74af93a45528faef4a2a9da27002021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86270-7https://doaj.org/toc/2045-2322Abstract Natural memories are associative, declarative and distributed, and memory retrieval is a constructive operation. In addition, cues of objects that are not contained in the memory are rejected directly. Symbolic computing memories resemble natural memories in their declarative character, and information can be stored and recovered explicitly; however, they are reproductive rather than constructive, and lack the associative and distributed properties. Sub-symbolic memories developed within the connectionist or artificial neural networks paradigm are associative and distributed, but lack the declarative property, the capability of rejecting objects that are not included in the memory, and memory retrieval is also reproductive. In this paper we present a memory model that sustains the five properties of natural memories. We use Relational-Indeterminate Computing to model associative memory registers that hold distributed representations of individual objects. This mode of computing has an intrinsic computing entropy which measures the indeterminacy of representations. This parameter determines the operational characteristics of the memory. Associative registers are embedded in an architecture that maps concrete images expressed in modality specific buffers into abstract representations and vice versa. The framework has been used to model a visual memory holding the representations of hand-written digits. The system has been tested with a set of memory recognition and retrieval experiments with complete and severely occluded images. The results show that there is a range of entropy values, not too low and not too high, in which associative memory registers have a satisfactory performance. The experiments were implemented in a simulation using a standard computer with a GPU, but a parallel architecture may be built where the memory operations would take a very reduced number of computing steps.Luis A. PinedaGibrán FuentesRafael MoralesNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Luis A. Pineda
Gibrán Fuentes
Rafael Morales
An entropic associative memory
description Abstract Natural memories are associative, declarative and distributed, and memory retrieval is a constructive operation. In addition, cues of objects that are not contained in the memory are rejected directly. Symbolic computing memories resemble natural memories in their declarative character, and information can be stored and recovered explicitly; however, they are reproductive rather than constructive, and lack the associative and distributed properties. Sub-symbolic memories developed within the connectionist or artificial neural networks paradigm are associative and distributed, but lack the declarative property, the capability of rejecting objects that are not included in the memory, and memory retrieval is also reproductive. In this paper we present a memory model that sustains the five properties of natural memories. We use Relational-Indeterminate Computing to model associative memory registers that hold distributed representations of individual objects. This mode of computing has an intrinsic computing entropy which measures the indeterminacy of representations. This parameter determines the operational characteristics of the memory. Associative registers are embedded in an architecture that maps concrete images expressed in modality specific buffers into abstract representations and vice versa. The framework has been used to model a visual memory holding the representations of hand-written digits. The system has been tested with a set of memory recognition and retrieval experiments with complete and severely occluded images. The results show that there is a range of entropy values, not too low and not too high, in which associative memory registers have a satisfactory performance. The experiments were implemented in a simulation using a standard computer with a GPU, but a parallel architecture may be built where the memory operations would take a very reduced number of computing steps.
format article
author Luis A. Pineda
Gibrán Fuentes
Rafael Morales
author_facet Luis A. Pineda
Gibrán Fuentes
Rafael Morales
author_sort Luis A. Pineda
title An entropic associative memory
title_short An entropic associative memory
title_full An entropic associative memory
title_fullStr An entropic associative memory
title_full_unstemmed An entropic associative memory
title_sort entropic associative memory
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/23c7c74af93a45528faef4a2a9da2700
work_keys_str_mv AT luisapineda anentropicassociativememory
AT gibranfuentes anentropicassociativememory
AT rafaelmorales anentropicassociativememory
AT luisapineda entropicassociativememory
AT gibranfuentes entropicassociativememory
AT rafaelmorales entropicassociativememory
_version_ 1718395270619725824