Incremental and developmental perspectives for general-purpose learning systems

The stupefying success of Articial Intelligence (AI) for specic problems, from recommender systems to self-driving cars, has not yet been matched with a similar progress in general AI systems, coping with a variety of (dierent) problems. This dissertation deals with the long-standing problem of crea...

Full description

Bibliographic Details
Main Author: Fernando Martínez-Plumed
Format: Article
Language:English
Published: Asociación Española para la Inteligencia Artificial 2017-02-01
Series:Inteligencia Artificial
Online Access:http://journal.iberamia.org/index.php/intartif/article/view/23
_version_ 1818914469334482944
author Fernando Martínez-Plumed
author_facet Fernando Martínez-Plumed
author_sort Fernando Martínez-Plumed
collection DOAJ
description The stupefying success of Articial Intelligence (AI) for specic problems, from recommender systems to self-driving cars, has not yet been matched with a similar progress in general AI systems, coping with a variety of (dierent) problems. This dissertation deals with the long-standing problem of creating more general AI systems, through the analysis of their development and the evaluation of their cognitive abilities. It presents a declarative general-purpose learning system and a developmental and lifelong approach for knowledge acquisition, consolidation and forgetting. It also analyses the use of the use of more ability-oriented evaluation techniques for AI evaluation and provides further insight for the understanding of the concepts of development and incremental learning in AI systems.
first_indexed 2024-12-19T23:46:53Z
format Article
id doaj.art-a9aa79bf7a8349eeaa12ec9de75a7896
institution Directory Open Access Journal
issn 1137-3601
1988-3064
language English
last_indexed 2024-12-19T23:46:53Z
publishDate 2017-02-01
publisher Asociación Española para la Inteligencia Artificial
record_format Article
series Inteligencia Artificial
spelling doaj.art-a9aa79bf7a8349eeaa12ec9de75a78962022-12-21T20:01:17ZengAsociación Española para la Inteligencia ArtificialInteligencia Artificial1137-36011988-30642017-02-012060242710.4114/intartif.vol20iss60pp24-2723Incremental and developmental perspectives for general-purpose learning systemsFernando Martínez-Plumed0UPVThe stupefying success of Articial Intelligence (AI) for specic problems, from recommender systems to self-driving cars, has not yet been matched with a similar progress in general AI systems, coping with a variety of (dierent) problems. This dissertation deals with the long-standing problem of creating more general AI systems, through the analysis of their development and the evaluation of their cognitive abilities. It presents a declarative general-purpose learning system and a developmental and lifelong approach for knowledge acquisition, consolidation and forgetting. It also analyses the use of the use of more ability-oriented evaluation techniques for AI evaluation and provides further insight for the understanding of the concepts of development and incremental learning in AI systems.http://journal.iberamia.org/index.php/intartif/article/view/23
spellingShingle Fernando Martínez-Plumed
Incremental and developmental perspectives for general-purpose learning systems
Inteligencia Artificial
title Incremental and developmental perspectives for general-purpose learning systems
title_full Incremental and developmental perspectives for general-purpose learning systems
title_fullStr Incremental and developmental perspectives for general-purpose learning systems
title_full_unstemmed Incremental and developmental perspectives for general-purpose learning systems
title_short Incremental and developmental perspectives for general-purpose learning systems
title_sort incremental and developmental perspectives for general purpose learning systems
url http://journal.iberamia.org/index.php/intartif/article/view/23
work_keys_str_mv AT fernandomartinezplumed incrementalanddevelopmentalperspectivesforgeneralpurposelearningsystems