Theoretical evaluation of the computational capabilities of a random network with memristive connections

Creating computing systems that implement the information processing properties of biological brains can have several advantages in terms of computational and energy efficiency. The present work provides a numerical modeling tool to evaluate the computational capabilities of a neuromorphic hardware...

Full description

Autores:
Suárez Usme, Laura Estefany
Tipo de recurso:
Fecha de publicación:
2016
Institución:
Universidad de los Andes
Repositorio:
Séneca: repositorio Uniandes
Idioma:
eng
OAI Identifier:
oai:repositorio.uniandes.edu.co:1992/13855
Acceso en línea:
http://hdl.handle.net/1992/13855
Palabra clave:
Redes neurales (Neurobiología) - Investigaciones
Sistemas dinámicos - Investigaciones
Análisis numérico - Investigaciones
Ingeniería
Rights
openAccess
License
https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
id UNIANDES2_5fd328a01f2d09992bd70bf0a33a6a83
oai_identifier_str oai:repositorio.uniandes.edu.co:1992/13855
network_acronym_str UNIANDES2
network_name_str Séneca: repositorio Uniandes
repository_id_str
spelling Al consultar y hacer uso de este recurso, está aceptando las condiciones de uso establecidas por los autores.https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfinfo:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Nino, Juan Claudio0dd92367-ead2-4d19-bdbd-fd110783b6fa500Correal Nuñez, María Elsavirtual::9700-1Suárez Usme, Laura Estefany3a467f2c-14ab-4403-a45b-af4fe2485f1f500Valencia Arboleda, Carlos Felipe2018-09-28T10:58:22Z2018-09-28T10:58:22Z2016http://hdl.handle.net/1992/13855u729574.pdfinstname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/Creating computing systems that implement the information processing properties of biological brains can have several advantages in terms of computational and energy efficiency. The present work provides a numerical modeling tool to evaluate the computational capabilities of a neuromorphic hardware architecture consisting of a random network of memristive connections. This architecture is analyzed from the perspective of the Reservoir Computing approach. A simple methodology based on the definition of ordered and chaotic dynamical systems was used to determine the Separation and Fading Memory Properties of the architecture proposed as required by the aforementioned approach. Results show the potential use of these networks as reservoirs for the processing of time-varying inputs.Magíster en Ingeniería IndustrialMaestría43 hojasapplication/pdfengUniandesMaestría en Ingeniería IndustrialFacultad de IngenieríaDepartamento de Ingeniería Industrialinstname:Universidad de los Andesreponame:Repositorio Institucional SénecaTheoretical evaluation of the computational capabilities of a random network with memristive connectionsTrabajo de grado - Maestríainfo:eu-repo/semantics/masterThesishttp://purl.org/coar/version/c_970fb48d4fbd8a85Texthttp://purl.org/redcol/resource_type/TMRedes neurales (Neurobiología) - InvestigacionesSistemas dinámicos - InvestigacionesAnálisis numérico - InvestigacionesIngenieríaPublicationad8ede4e-d09b-4962-b576-aaec7abe3227virtual::9700-1ad8ede4e-d09b-4962-b576-aaec7abe3227virtual::9700-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000512087virtual::9700-1THUMBNAILu729574.pdf.jpgu729574.pdf.jpgIM Thumbnailimage/jpeg8140https://repositorio.uniandes.edu.co/bitstreams/f0d20e92-420d-484e-b556-f884ac0ad868/download67e6f656b5d03f8c43539d5681126895MD55ORIGINALu729574.pdfapplication/pdf14450568https://repositorio.uniandes.edu.co/bitstreams/1b03bf13-57cd-4d92-b8c7-1e4612600e3a/downloadaea84f423bc6e33cad0e62355c028f91MD51TEXTu729574.pdf.txtu729574.pdf.txtExtracted texttext/plain88302https://repositorio.uniandes.edu.co/bitstreams/fb9d3176-836f-4f69-a3c7-f284850a1b2d/download4d9b836ee6f79f1c3a8aa25c57ffcebfMD541992/13855oai:repositorio.uniandes.edu.co:1992/138552024-03-13 14:00:03.594https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdfopen.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.co
dc.title.es_CO.fl_str_mv Theoretical evaluation of the computational capabilities of a random network with memristive connections
title Theoretical evaluation of the computational capabilities of a random network with memristive connections
spellingShingle Theoretical evaluation of the computational capabilities of a random network with memristive connections
Redes neurales (Neurobiología) - Investigaciones
Sistemas dinámicos - Investigaciones
Análisis numérico - Investigaciones
Ingeniería
title_short Theoretical evaluation of the computational capabilities of a random network with memristive connections
title_full Theoretical evaluation of the computational capabilities of a random network with memristive connections
title_fullStr Theoretical evaluation of the computational capabilities of a random network with memristive connections
title_full_unstemmed Theoretical evaluation of the computational capabilities of a random network with memristive connections
title_sort Theoretical evaluation of the computational capabilities of a random network with memristive connections
dc.creator.fl_str_mv Suárez Usme, Laura Estefany
dc.contributor.advisor.none.fl_str_mv Nino, Juan Claudio
Correal Nuñez, María Elsa
dc.contributor.author.none.fl_str_mv Suárez Usme, Laura Estefany
dc.contributor.jury.none.fl_str_mv Valencia Arboleda, Carlos Felipe
dc.subject.keyword.es_CO.fl_str_mv Redes neurales (Neurobiología) - Investigaciones
Sistemas dinámicos - Investigaciones
Análisis numérico - Investigaciones
topic Redes neurales (Neurobiología) - Investigaciones
Sistemas dinámicos - Investigaciones
Análisis numérico - Investigaciones
Ingeniería
dc.subject.themes.none.fl_str_mv Ingeniería
description Creating computing systems that implement the information processing properties of biological brains can have several advantages in terms of computational and energy efficiency. The present work provides a numerical modeling tool to evaluate the computational capabilities of a neuromorphic hardware architecture consisting of a random network of memristive connections. This architecture is analyzed from the perspective of the Reservoir Computing approach. A simple methodology based on the definition of ordered and chaotic dynamical systems was used to determine the Separation and Fading Memory Properties of the architecture proposed as required by the aforementioned approach. Results show the potential use of these networks as reservoirs for the processing of time-varying inputs.
publishDate 2016
dc.date.issued.es_CO.fl_str_mv 2016
dc.date.accessioned.none.fl_str_mv 2018-09-28T10:58:22Z
dc.date.available.none.fl_str_mv 2018-09-28T10:58:22Z
dc.type.spa.fl_str_mv Trabajo de grado - Maestría
dc.type.coarversion.fl_str_mv http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/masterThesis
dc.type.content.spa.fl_str_mv Text
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/TM
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/1992/13855
dc.identifier.pdf.none.fl_str_mv u729574.pdf
dc.identifier.instname.spa.fl_str_mv instname:Universidad de los Andes
dc.identifier.reponame.spa.fl_str_mv reponame:Repositorio Institucional Séneca
dc.identifier.repourl.spa.fl_str_mv repourl:https://repositorio.uniandes.edu.co/
url http://hdl.handle.net/1992/13855
identifier_str_mv u729574.pdf
instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
repourl:https://repositorio.uniandes.edu.co/
dc.language.iso.es_CO.fl_str_mv eng
language eng
dc.rights.uri.*.fl_str_mv https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.es_CO.fl_str_mv 43 hojas
dc.format.mimetype.es_CO.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Uniandes
dc.publisher.program.es_CO.fl_str_mv Maestría en Ingeniería Industrial
dc.publisher.faculty.es_CO.fl_str_mv Facultad de Ingeniería
dc.publisher.department.es_CO.fl_str_mv Departamento de Ingeniería Industrial
publisher.none.fl_str_mv Uniandes
dc.source.es_CO.fl_str_mv instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
instname_str Universidad de los Andes
institution Universidad de los Andes
reponame_str Repositorio Institucional Séneca
collection Repositorio Institucional Séneca
bitstream.url.fl_str_mv https://repositorio.uniandes.edu.co/bitstreams/f0d20e92-420d-484e-b556-f884ac0ad868/download
https://repositorio.uniandes.edu.co/bitstreams/1b03bf13-57cd-4d92-b8c7-1e4612600e3a/download
https://repositorio.uniandes.edu.co/bitstreams/fb9d3176-836f-4f69-a3c7-f284850a1b2d/download
bitstream.checksum.fl_str_mv 67e6f656b5d03f8c43539d5681126895
aea84f423bc6e33cad0e62355c028f91
4d9b836ee6f79f1c3a8aa25c57ffcebf
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
repository.name.fl_str_mv Repositorio institucional Séneca
repository.mail.fl_str_mv adminrepositorio@uniandes.edu.co
_version_ 1818111867041611776

Publicaciones similares