This HTML5 document contains 389 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
dbthttp://dbpedia.org/resource/Template:
wikipedia-enhttp://en.wikipedia.org/wiki/
dbrhttp://dbpedia.org/resource/
n6https://ojs.aaai.org/index.php/aimagazine/article/view/
n22https://web.archive.org/web/20200726131654/https:/archive.org/details/
n24https://web.archive.org/web/20070515072641/http:/www.inf.ed.ac.uk/about/
n32http://www.neural-symbolic.org/
n18https://cacm.acm.org/magazines/2010/6/92472-an-interview-with-ed-feigenbaum/
dctermshttp://purl.org/dc/terms/
rdfshttp://www.w3.org/2000/01/rdf-schema#
n23https://dx.doi.org/10.1016/
dbpedia-azhttp://az.dbpedia.org/resource/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
dbphttp://dbpedia.org/property/
xsdhhttp://www.w3.org/2001/XMLSchema#
n29https://doi.org/10.1093/mind/
dbohttp://dbpedia.org/ontology/
dbpedia-vihttp://vi.dbpedia.org/resource/
n26https://lib.dr.iastate.edu/cgi/
dbchttp://dbpedia.org/resource/Category:
n12http://dbpedia.org/resource/Artificial_Intelligence:
n27http://arxiv.org/abs/
n13https://www.youtube.com/
n11http://www.cogsci.ucsd.edu/~coulson/203/
dbpedia-ruhttp://ru.dbpedia.org/resource/
dbpedia-rohttp://ro.dbpedia.org/resource/
wikidatahttp://www.wikidata.org/entity/
goldhttp://purl.org/linguistics/gold/
n21https://global.dbpedia.org/id/
n30https://web.archive.org/web/20070103222615/http:/www.engagingexperience.com/2006/07/
n39http://www.inf.ed.ac.uk/about/
dbpedia-ithttp://it.dbpedia.org/resource/
dbpedia-cahttp://ca.dbpedia.org/resource/
n40http://www.engagingexperience.com/2006/07/
provhttp://www.w3.org/ns/prov#
n16https://aaai-2022.virtualchair.net/
foafhttp://xmlns.com/foaf/0.1/
dbpedia-zhhttp://zh.dbpedia.org/resource/
dbpedia-fahttp://fa.dbpedia.org/resource/
dbpedia-trhttp://tr.dbpedia.org/resource/
n25https://archive.org/details/
dbpedia-eshttp://es.dbpedia.org/resource/
freebasehttp://rdf.freebase.com/ns/
owlhttp://www.w3.org/2002/07/owl#

Statements

Subject Item
dbr:Symbolic_artificial_intelligence
rdfs:label
Intelligenza artificiale simbolica Intel·ligència artificial simbòlica Символический искусственный интеллект 符號人工智能 Symbolic artificial intelligence Inteligencia artificial simbólica
rdfs:comment
L'intelligenza artificiale simbolica indica i metodi nella ricerca sull'intelligenza artificiale che si basano su rappresentazioni di problemi "simboliche" di (leggibili dall'uomo), logica e ricerca. L'IA simbolica è stata il paradigma dominante della ricerca sull'IA dalla metà degli anni '50 fino alla fine degli anni '80. In artificial intelligence, symbolic artificial intelligence is the term for the collection of all methods in artificial intelligence research that are based on high-level symbolic (human-readable) representations of problems, logic and search. Symbolic AI used tools such as logic programming, production rules, semantic nets and frames, and it developed applications such as knowledge-based systems (in particular, expert systems), symbolic mathematics, automated theorem provers, ontologies, the semantic web, and automated planning and scheduling systems. The Symbolic AI paradigm led to seminal ideas in search, symbolic programming languages, agents, multi-agent systems, the semantic web, and the strengths and limitations of formal knowledge and reasoning systems. Символический искусственный интеллект — собирательное название для всех методов исследования искусственного интеллекта, основанных на высокоуровневом «символическом» (человекочитаемом) представлении задач, логики и поиска. Символический ИИ лёг в основу доминирующей парадигмы исследований ИИ с середины 1950-х до конца 1980-х. Inteligencia artificial simbólica es el nombre colectivo para todos los métodos de investigación de la inteligencia artificial que se basan en representaciones de alto nivel "simbólico" de los problemas, la lógica matemática y la búsqueda. IA simbólica fue el paradigma dominante de la investigación en IA desde mediados de los cincuenta hasta finales de los años ochenta. Después, se introdujeron enfoques sub-simbólicos más recientes a la IA, basado en redes neuronales, estadística, optimización numérica y otras técnicas. La IA simbólica se sigue aplicando en algunos dominios más pequeños (como la representación del conocimiento), pero la mayoría de las aplicaciones de IA en el siglo XXI no emplean símbolos legibles como sus objetos primarios. La intel·ligència artificial simbòlica, també anomenada GOFAI (les sigles de Good Old-Fashioned AI) es refereix a la intel·ligència artificial més primitiva, clàssica i simbòlica. La intel·ligència artificial normal, en canvi, engloba programació i robòtica evolucionada. L’objectiu d’aquesta és construir sistemes informàtics útils que substitueixin o ajudin a tasques humanes. L’objectiu de la GOFAI, en canvi, és desenvolupar teories de la ment explicatives. 符号人工智慧(英語:Symbolic artificial intelligence)是人工智慧研究中的一個集合術語,泛指所有「基於問題、逻辑和搜索的高級『符號』(人類可讀)表徵」的方法。从1950年代中期到1980年代后期,符號AI一直是AI研究的主要范式 。 1985年,在他的書《 人工智慧:非常的想法 》中探讨了人工智慧研究的哲学含义,将符號人工智慧命名为GOFAI(Good Old-Fashioned Artificial Intelligence,指的是“有效的老式人工智慧)。在机器人学領域 ,类似的术语是GOFR(“有效的老式机器人学”)。 该方法基于这样的假设:「智慧的许多特征可以透過符号處理来实现。」在1960年代中期,艾伦·纽厄尔和赫伯特·西蒙將該假设定义为「物理符号系统假設」。 符號人工智慧中,有一種常用的形式是专家系统 ,該系統使用產出規則網路。產出規則是以类似「If-Then语句的关系」來连接符号。专家系统會使用人类可读的符号來处理规则,藉此进行推論,并确定還需要哪些其他信息,也就是還要问什么问题。 符號方法的反对者包括罗德尼·布鲁克斯等機器人學專家 ,他们打算生产無符號表徵(或仅具最低限度的表徵)的自律機器人,其它反对者還包括研究人员,他们应用诸如人工神经网络和最佳化之类的技术来解决机器学习和控制工程中的问题 。
dcterms:subject
dbc:Artificial_intelligence
dbo:wikiPageID
339417
dbo:wikiPageRevisionID
1124907986
dbo:wikiPageWikiLink
dbr:Knowledge-based_system dbr:Distributed_constraint_optimization dbr:Argumentation_framework dbr:Conceptual_graphs dbr:Symbolic_mathematics dbr:Backpropagation dbr:Carl_Hewitt dbr:James_F._Allen_(computer_scientist) dbr:Lofti_Zadeh dbr:Horn_clauses dbr:Computing_Machinery_and_Intelligence dbr:BERT_(language_model) dbr:GPUs dbr:Eurisko dbr:Cooperative_distributed_problem_solving dbr:Sudoku dbr:Roger_Schank dbr:Higher-order_functions dbr:Gradient_descent dbr:Consensus_dynamics dbr:Shallow_parsing dbr:Herbert_A._Simon dbr:Logic_theorist dbr:Deep_learning dbr:Verbal_arithmetic dbr:Peter_Norvig n12:_A_Modern_Approach dbr:John_Robert_Anderson_(psychologist) dbr:Gary_Marcus dbr:Non-monotonic_reasoning dbr:Drools dbr:Mace4 dbr:First-order_logic dbr:Stanford dbr:Automated_theorem_proving dbr:Tokenizing dbr:Automated_reasoning dbr:Automated_planning_and_scheduling dbr:Conflict-driven_clause_learning dbr:University_of_Edinburgh dbr:Machine_learning dbr:Waldinger dbr:Artificial_neural_network dbr:Association_rule_learning dbr:Belief–desire–intention_software_model dbr:Disease_Ontology dbr:Genetic_algorithms dbr:Belief_revision dbr:Stanford_Artificial_Intelligence_Laboratory dbr:Logic_programming dbr:Chess dbr:Search_algorithm dbr:Backtracking dbr:Texas_Instruments dbr:Ontologies dbr:John_Haugeland dbr:CLOS dbr:Neats_and_scruffies dbr:Pantheon_Books dbr:Prolog dbr:Parsing dbr:YAGO_(database) dbr:Management_science dbr:Toy_problem dbr:CADUCEUS_(expert_system) dbr:Alain_Colmerauer dbr:Ontology_(information_science) dbr:Garbage_collection_(computer_science) dbr:Connectionism dbr:Henry_Kautz dbr:Intelligent_tutoring_systems dbr:Python_(programming_language) dbr:Flavors_(programming_language) dbr:Knowledge_base dbr:Truth_maintenance_system dbr:Semantic_nets dbr:Connection_Machine dbr:Backward_chaining dbr:MIT dbr:Web_Ontology_Language dbr:Decision-tree dbr:CLIPS dbr:Multiple_inheritance dbr:Alpha-beta_pruning dbr:Depth-first_search dbr:Read-eval-print_loop dbr:Part-of-speech_tagging dbr:Modal_logic dbr:Monte_Carlo_tree_search dbr:Allen_Newell dbr:Intelligent_tutoring_system dbr:Hybrid_intelligent_system dbr:Qualification_problem dbr:ACT-R dbr:Probabilistic_logic dbr:Checkers dbr:Andy_Clark dbr:Soar_(cognitive_architecture) dbr:Production_(computer_science) dbr:Alan_Turing dbr:Stanford_Research_Institute_Problem_Solver dbr:Knowledge_representation_and_reasoning dbr:Ed_Feigenbaum dbr:Reinforcement_learning dbr:Knowledge_representation dbr:Multi-agent_planning dbr:Francesca_Rossi dbr:Doug_Lenat dbr:Probably_approximately_correct_learning dbr:Statistical_relational_learning dbr:AI@50 dbr:Benjamin_Kuipers dbr:Vampire_(theorem_prover) dbr:Marvin_Minsky dbr:Declarative_programming dbr:Generative_adversarial_network dbr:Horn_clause dbr:Genetic_programming dbr:Cliff_Shaw dbr:Latent_semantic_analysis dbr:Lighthill_report dbr:Fuzzy_logic dbr:Dendral dbr:Lisp_Machines dbr:Meta-object_protocol dbr:Computer_vision dbr:Subsumption_architecture dbr:Seymour_Papert dbr:Multi-paradigm_programming_language dbr:Rodney_Brooks dbr:Decision_tree_learning dbr:Functional_programming dbr:Unique_name_assumption dbr:Multi-agent_systems dbr:Knowledge_Query_and_Manipulation_Language dbr:Garry_Kasparov dbr:Traveller_(role-playing_game) dbr:Multi-agent_system dbr:Ross_Quinlan dbr:Metaclasses dbr:Boolean_satisfiability_problem dbr:Behavior-based_robotics dbr:Version_space_learning dbr:Self-hosting_(compilers) dbr:Planner_(programming_language) dbr:Prover9 dbr:Nouvelle_AI dbr:Convolutional_neural_network dbr:Jess dbr:Spell_checker dbr:ACL2 dbr:Formal_logic dbr:Stanford_University dbr:Sequential_pattern_mining dbr:Markov_logic_network dbr:MYCIN dbr:Physical_symbol_systems_hypothesis dbr:Dynamic_typing dbr:Data_science dbr:Upper_ontology dbr:Region_connection_calculus dbr:Hidden_Markov_model dbr:WordNet dbr:Temporal_logic dbr:Script_theory dbr:Knowledge-based_systems dbr:OPS5 dbr:Internist-I dbr:Probabilistic_Soft_Logic dbr:Leslie_Valiant dbr:Inference_engine dbr:Psychology dbr:Judea_Pearl dbr:Commonsense_knowledge_bases dbr:Thinking,_Fast_and_Slow dbr:Douglas_Lenat dbr:Frame_(artificial_intelligence) dbr:Breadth-first_search dbr:Ehud_Shapiro dbr:Inference_Corporation dbr:Symbolics dbr:Artificial_intelligence dbr:Cognitive_model dbr:Paradigm dbr:PLANNER dbr:Yoshua_Bengio dbr:Cyc dbr:Yann_LeCun dbr:Artificial_general_intelligence dbr:Chunking_(psychology) dbr:Robert_Kowalski dbr:Means-ends_analysis dbr:Natural_language_processing dbr:DPLL_algorithm dbr:A*_search_algorithm dbr:Closed-world_assumption dbr:John_McCarthy_(computer_scientist) dbr:Conditional_(computer_programming) dbr:Deep_Blue_(chess_computer) dbr:Expert_system dbr:Situated_cognition dbr:Danny_Hillis dbr:Intelligent_agent dbr:Journal_of_the_American_Chemical_Society dbr:Synsets dbr:Object-oriented_programming dbr:Common_Lisp_Object_System dbr:Allen's_interval_algebra dbr:Inductive_logic_programming dbr:Constraint_logic_programming dbr:Knowledge_acquisition dbr:Constraint_programming dbr:Constraint_satisfaction dbr:Smalltalk dbr:Branch_and_bound dbr:Deductive_classifier dbr:Carl_Djerassi dbr:Stuart_J._Russell dbr:Reason_maintenance dbr:LISP_machine dbr:LISP_machines dbr:DENDRAL dbr:LISP_(programming_language) dbr:Epistemic_logic dbr:Hubert_Dreyfus dbr:Program_synthesis dbr:Principia_Mathematica dbr:Explicit_semantic_analysis dbr:Blackboard_system dbr:C4.5 dbr:Aether_(classical_element) dbr:Transformer_(machine_learning_model) dbr:Model-based_reasoning dbr:Joshua_Lederberg dbr:Bart_Selman dbr:Fifth_Generation_Project dbr:Recursion dbr:Neural_networks dbr:Bayesian_Networks dbr:GPT-3 dbr:Daniel_Kahneman dbr:Case-based_reasoning dbr:Nqthm dbr:Cognitive_science dbr:Region_Connection_Calculus dbr:Semantic_networks dbr:Blocks_world dbr:General_Problem_Solver dbr:Go_(game) dbr:Common_Lisp dbr:Communications_of_the_ACM dbr:Embodied_cognition dbr:Satplan dbr:Semantic_web dbr:Boolean_satisfiability dbr:Production_system_(computer_science) dbr:Glass_box dbr:Manna dbr:Perceptron dbr:Forward_chaining dbr:Automated_planning dbr:Imperative_programming dbr:Frank_Rosenblatt dbr:Neats_vs._scruffies dbr:History_of_AI dbr:Logic dbr:Macsyma dbr:Expert_systems dbr:Operations_research dbr:Bayesian_reasoning dbr:ID3_algorithm dbc:Artificial_intelligence dbr:IBM dbr:SHRDLU dbr:Logic_Theorist dbr:Commonsense_reasoning dbr:Digital_Equipment_Corporation dbr:Neuro-symbolic_AI dbr:XCON dbr:Constraint_handling_rules dbr:Unification_(computer_science) dbr:Heuristic_(computer_science) dbr:List_of_programming_languages_for_artificial_intelligence dbr:AlphaGo dbr:Automated_theorem_provers dbr:Tom_M._Mitchell dbr:Description_logic dbr:Carnegie_Mellon_University dbr:Semantic_Web dbr:Philosophy_of_artificial_intelligence dbr:Cognitive_architecture dbr:FORTRAN dbr:John_R._Koza dbr:Geoffrey_Hinton dbr:CommonLoops dbr:Graphplan dbr:Discourse_representation_theory dbr:Software_agent dbr:Edward_Feigenbaum dbr:Multi-agent_learning dbr:Cybernetics dbr:Minimax dbr:Wordle dbr:Wikipedia dbr:And–or_tree dbr:Arthur_Samuel dbr:History_of_artificial_intelligence dbr:Cognitive_tutors dbr:Pamela_McCorduck dbr:Hidden_Markov_Model dbr:Model_checking dbr:Protégé_(software) dbr:WalkSAT
dbo:wikiPageExternalLink
n6:19122 n11:dreyfus.pdf n13:watch%3Fv=_cQITY0SPiw n16:plenary_13.html n18:fulltext%7CAn n22:artificialintell0000nils n23:0004-3702%2891%2990053-M n24:AIhistory.html n25:artificialintell0000nils%7Curl-access=registration%7Caccess-date=18 n26:viewcontent.cgi%3Farticle=1072&context=cs_techreports n27:2002.06177 n27:2012.05876 n16:plenary_2.html n29:LIX.236.433 n30:ai50_ai_past_pr.html n32: n39:AIhistory.html n40:ai50_ai_past_pr.html n27:1606.04422 n27:1905.06088
owl:sameAs
dbpedia-zh:符號人工智能 dbpedia-ru:Символический_искусственный_интеллект freebase:m.01xwzj dbpedia-vi:GOFAI dbpedia-ro:Inteligență_artificială_simbolică dbpedia-az:Simvolik_süni_intellekt dbpedia-tr:Sembolik_yapay_zeka n21:4jUkc dbpedia-fa:هوش_مصنوعی_نمادین dbpedia-it:Intelligenza_artificiale_simbolica dbpedia-es:Inteligencia_artificial_simbólica wikidata:Q5514059 dbpedia-ca:Intel·ligència_artificial_simbòlica
dbp:wikiPageUsesTemplate
dbt:Citation dbt:Cite_AV_media dbt:Cite_conference dbt:Cite_book dbt:Cite_journal dbt:Cite_web dbt:Efn dbt:Main dbt:Reflist dbt:Artificial_intelligence dbt:Notelist dbt:Blockquote dbt:McCorduck_2004 dbt:Crevier_1993 dbt:Sfn dbt:Cite_techreport dbt:Short_description dbt:Russell_Norvig_2003
dbo:abstract
符号人工智慧(英語:Symbolic artificial intelligence)是人工智慧研究中的一個集合術語,泛指所有「基於問題、逻辑和搜索的高級『符號』(人類可讀)表徵」的方法。从1950年代中期到1980年代后期,符號AI一直是AI研究的主要范式 。 1985年,在他的書《 人工智慧:非常的想法 》中探讨了人工智慧研究的哲学含义,将符號人工智慧命名为GOFAI(Good Old-Fashioned Artificial Intelligence,指的是“有效的老式人工智慧)。在机器人学領域 ,类似的术语是GOFR(“有效的老式机器人学”)。 该方法基于这样的假设:「智慧的许多特征可以透過符号處理来实现。」在1960年代中期,艾伦·纽厄尔和赫伯特·西蒙將該假设定义为「物理符号系统假設」。 符號人工智慧中,有一種常用的形式是专家系统 ,該系統使用產出規則網路。產出規則是以类似「If-Then语句的关系」來连接符号。专家系统會使用人类可读的符号來处理规则,藉此进行推論,并确定還需要哪些其他信息,也就是還要问什么问题。 符號方法的反对者包括罗德尼·布鲁克斯等機器人學專家 ,他们打算生产無符號表徵(或仅具最低限度的表徵)的自律機器人,其它反对者還包括研究人员,他们应用诸如人工神经网络和最佳化之类的技术来解决机器学习和控制工程中的问题 。 符號人工智慧的目的是在機器中產生通用的、類人的智慧,而大多數現代研究是針對特定的子問題。目前對通用智慧的研究集中在通用人工智慧的子领域中 。 最初,機器被設計成「根據符號表示的輸入」來制定輸出。當輸入是明確的且屬於確定性時,輸出就會使用符號。但是,當存在不確定性時,表徵會使用"模糊逻辑"完成(例如,在制定預測的時候)。這在人工神经网络中可以看到。 In artificial intelligence, symbolic artificial intelligence is the term for the collection of all methods in artificial intelligence research that are based on high-level symbolic (human-readable) representations of problems, logic and search. Symbolic AI used tools such as logic programming, production rules, semantic nets and frames, and it developed applications such as knowledge-based systems (in particular, expert systems), symbolic mathematics, automated theorem provers, ontologies, the semantic web, and automated planning and scheduling systems. The Symbolic AI paradigm led to seminal ideas in search, symbolic programming languages, agents, multi-agent systems, the semantic web, and the strengths and limitations of formal knowledge and reasoning systems. Symbolic AI was the dominant paradigm of AI research from the mid-1950s until the middle 1990s. Researchers in the 1960s and the 1970s were convinced that symbolic approaches would eventually succeed in creating a machine with artificial general intelligence and considered this the ultimate goal of their field. An early boom, with early successes such as the Logic Theorist and Samuel's Checker's Playing Program led to unrealistic expectations and promises and was followed by the First AI Winter as funding dried up. A second boom (1969–1986) occurred with the rise of expert systems, their promise of capturing corporate expertise, and an enthusiastic corporate embrace. That boom, and some early successes, e.g., with XCON at DEC, was followed again by later disappointment. Problems with difficulties in knowledge acquisition, maintaining large knowledge bases, and brittleness in handling out-of-domain problems arose. Another, second, AI Winter (1988–2011) followed. Subsequently, AI researchers focused on addressing underlying problems in handling uncertainty and in knowledge acquisition. Uncertainty was addressed with formal methods such as hidden Markov models, Bayesian reasoning, and statistical relational learning. Symbolic machine learning addressed the knowledge acquisition problem with contributions including Version Space, Valiant's PAC learning, Quinlan's ID3 decision-tree learning, case-based learning, and inductive logic programming to learn relations. Neural networks, a sub-symbolic approach, had been pursued from early days and was to reemerge strongly in 2012. Early examples are Rosenblatt's perceptron learning work, the backpropagation work of Rumelhart, Hinton and Williams, and work in convolutional neural networks by LeCun et al. in 1989. However, neural networks were not viewed as successful until about 2012: "Until Big Data became commonplace, the general consensus in the Al community was that the so-called neural-network approach was hopeless. Systems just didn't work that well, compared to other methods. ... A revolution came in 2012, when a number of people, including a team of researchers working with Hinton, worked out a way to use the power of GPUs to enormously increase the power of neural networks." Over the next several years, deep learning had spectacular success in handling vision, speech recognition, speech synthesis, image generation, and machine translation. However, since 2020, as inherent difficulties with bias, explanation, comprehensibility, and robustness became more apparent with deep learning approaches; an increasing number of AI researchers have called for combining the best of both the symbolic and neural network approaches and addressing areas that both approaches have difficulty with, such as common-sense reasoning. La intel·ligència artificial simbòlica, també anomenada GOFAI (les sigles de Good Old-Fashioned AI) es refereix a la intel·ligència artificial més primitiva, clàssica i simbòlica. La intel·ligència artificial normal, en canvi, engloba programació i robòtica evolucionada. L’objectiu d’aquesta és construir sistemes informàtics útils que substitueixin o ajudin a tasques humanes. L’objectiu de la GOFAI, en canvi, és desenvolupar teories de la ment explicatives. Символический искусственный интеллект — собирательное название для всех методов исследования искусственного интеллекта, основанных на высокоуровневом «символическом» (человекочитаемом) представлении задач, логики и поиска. Символический ИИ лёг в основу доминирующей парадигмы исследований ИИ с середины 1950-х до конца 1980-х. В 1985 году (англ. John Haugeland) дал символическому ИИ название GOFAI (англ. Good Old-Fashioned Artificial Intelligence, «старый добрый искусственный интеллект») в своей книге Artificial Intelligence: The Very Idea, посвящённой философскому отражению последствий исследований искусственного интеллекта. В робототехнике применяется аналогичный термин GOFAIR («старый добрый искусственный интеллект в робототехнике»). Наиболее успешная форма символического ИИ — это экспертные системы, использующие сеть продукционных правил. Продукционные правила объединяют символы в отношения, похожие на оператор «если-то». Экспертная система, обрабатывая эти правила, делает логические выводы и определяет, какая дополнительная информация ей необходима, то есть какие следует задать вопросы, используя человекочитаемые символы. L'intelligenza artificiale simbolica indica i metodi nella ricerca sull'intelligenza artificiale che si basano su rappresentazioni di problemi "simboliche" di (leggibili dall'uomo), logica e ricerca. L'IA simbolica è stata il paradigma dominante della ricerca sull'IA dalla metà degli anni '50 fino alla fine degli anni '80. Inteligencia artificial simbólica es el nombre colectivo para todos los métodos de investigación de la inteligencia artificial que se basan en representaciones de alto nivel "simbólico" de los problemas, la lógica matemática y la búsqueda. IA simbólica fue el paradigma dominante de la investigación en IA desde mediados de los cincuenta hasta finales de los años ochenta. Después, se introdujeron enfoques sub-simbólicos más recientes a la IA, basado en redes neuronales, estadística, optimización numérica y otras técnicas. La IA simbólica se sigue aplicando en algunos dominios más pequeños (como la representación del conocimiento), pero la mayoría de las aplicaciones de IA en el siglo XXI no emplean símbolos legibles como sus objetos primarios. dio el nombre GOFAI (por sus siglas en inglés, Good Old-Fashioned Artificial Intelligence) a la IA simbólica en su libro de 1985 Inteligencia Artificial: La Idea Pura, que exploró las implicaciones filosóficas de la investigación de la inteligencia artificial. En robótica el término análogo es GOFAIR (por sus siglas en inglés, "Good Old-Fashioned Robotics"). Este enfoque se basa en la suposición de que muchos aspectos de la inteligencia se pueden lograr mediante la manipulación de símbolos, un supuesto definido como la "" por Allen Newell y Herbert A. Simon a mediados de los años 60’s: La forma más exitosa de la IA simbólica son los sistemas expertos, los cuales utilizan una red de . Las normas de producción conectan símbolos en una relación similar a una instrucción “Si-Entonces” (If-Then). El sistema experto procesa las reglas para hacer deducciones y determinar qué información adicional se necesita, por ejemplo, qué preguntas hacer, usando simbología legible para el ser humano. Los opositores a la aproximación simbólica incluyen a expertos en robótica como Rodney Brooks, quien tiene como objetivo producir robots autónomos sin representación simbólica (o con sólo una mínima representación) y los investigadores de inteligencia computacional, que aplican técnicas como las redes neuronales y optimización para resolver problemas en el aprendizaje automático y la ingeniería de control. La IA simbólica estaba destinada a producir inteligencia similar a la humana en una máquina, mientras que la mayor parte de la investigación moderna se dirige a subproblemas específicos. La investigación sobre la inteligencia general está en estudio del subcampo llamado Inteligencia Artificial General.
gold:hypernym
dbr:Name
prov:wasDerivedFrom
wikipedia-en:Symbolic_artificial_intelligence?oldid=1124907986&ns=0
dbo:wikiPageLength
86699
foaf:isPrimaryTopicOf
wikipedia-en:Symbolic_artificial_intelligence