Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2401.07744 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929247441911808 |
|---|---|
| author | Ghidalia, Sarah Narsis, Ouassila Labbani Bertaux, Aurélie Nicolle, Christophe |
| author_facet | Ghidalia, Sarah Narsis, Ouassila Labbani Bertaux, Aurélie Nicolle, Christophe |
| contents | Motivated by the desire to explore the process of combining inductive and deductive reasoning, we conducted a systematic literature review of articles that investigate the integration of machine learning and ontologies. The objective was to identify diverse techniques that incorporate both inductive reasoning (performed by machine learning) and deductive reasoning (performed by ontologies) into artificial intelligence systems. Our review, which included the analysis of 128 studies, allowed us to identify three main categories of hybridization between machine learning and ontologies: learning-enhanced ontologies, semantic data mining, and learning and reasoning systems. We provide a comprehensive examination of all these categories, emphasizing the various machine learning algorithms utilized in the studies. Furthermore, we compared our classification with similar recent work in the field of hybrid AI and neuro-symbolic approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07744 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Combining Machine Learning and Ontology: A Systematic Literature Review Ghidalia, Sarah Narsis, Ouassila Labbani Bertaux, Aurélie Nicolle, Christophe Artificial Intelligence Machine Learning Motivated by the desire to explore the process of combining inductive and deductive reasoning, we conducted a systematic literature review of articles that investigate the integration of machine learning and ontologies. The objective was to identify diverse techniques that incorporate both inductive reasoning (performed by machine learning) and deductive reasoning (performed by ontologies) into artificial intelligence systems. Our review, which included the analysis of 128 studies, allowed us to identify three main categories of hybridization between machine learning and ontologies: learning-enhanced ontologies, semantic data mining, and learning and reasoning systems. We provide a comprehensive examination of all these categories, emphasizing the various machine learning algorithms utilized in the studies. Furthermore, we compared our classification with similar recent work in the field of hybrid AI and neuro-symbolic approaches. |
| title | Combining Machine Learning and Ontology: A Systematic Literature Review |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.07744 |