Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature
The need for neural-symbolic integration becomes apparent as more complex problems are tackled, and they go beyond limited domain tasks such as classification. In this sense, understanding the state of the art of hybrid technologies based on Deep Learning and augmented with logic based systems, is...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Asociación Española para la Inteligencia Artificial
2022-03-01
|
| Series: | Inteligencia Artificial |
| Subjects: | |
| Online Access: | https://journal.iberamia.org/index.php/intartif/article/view/702 |
| _version_ | 1811294294768615424 |
|---|---|
| author | Pablo Negro Claudia Pons |
| author_facet | Pablo Negro Claudia Pons |
| author_sort | Pablo Negro |
| collection | DOAJ |
| description |
The need for neural-symbolic integration becomes apparent as more complex problems are tackled, and they go beyond limited domain tasks such as classification. In this sense, understanding the state of the art of hybrid technologies based on Deep Learning and augmented with logic based systems, is of utmost importance. As a consequence, we seek to understand and represent the current state of these technologies that are highly used in intelligent systems engineering.
This work aims to provide a comprehensive view of the solutions available in the literature, within the field of applied Artificial Intelligence (AI), using technologies based on AI techniques that integrate symbolic and non-symbolic logic (in particular artificial neural networks), making them the subject of a systematic literature review (SLR).
The resulting technologies are discussed and evaluated from both perspectives: symbolic and non-symbolic AI.
In this work, we use the PICOC & Limits method to define the research questions and analyze the results.
Out of a total of 65 candidate studies found, 24 articles (37%) relevant to this study were selected. Each study also focuses on different application domains. Conclusion: Through the analysis of the selected works throughout this review, we have seen different combinations of logical systems with some form of neural network and, although we have not found a clear architectural pattern, efforts to find a model of general purpose combining both worlds drive trends and research efforts.
|
| first_indexed | 2024-04-13T05:15:21Z |
| format | Article |
| id | doaj.art-13ba269615da4fe6a1d24d8768fef8a7 |
| institution | Directory Open Access Journal |
| issn | 1137-3601 1988-3064 |
| language | English |
| last_indexed | 2024-04-13T05:15:21Z |
| publishDate | 2022-03-01 |
| publisher | Asociación Española para la Inteligencia Artificial |
| record_format | Article |
| series | Inteligencia Artificial |
| spelling | doaj.art-13ba269615da4fe6a1d24d8768fef8a72022-12-22T03:00:55ZengAsociación Española para la Inteligencia ArtificialInteligencia Artificial1137-36011988-30642022-03-01256910.4114/intartif.vol25iss69pp13-41Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literaturePablo Negro0Claudia Pons1CAETI - Center for Higher Studies in Information Technology, Faculty of Technology. UAI., ArgerntinaCAETI - Center for Higher Studies in Information Technology, Faculty of Technology. UAI. Argentina The need for neural-symbolic integration becomes apparent as more complex problems are tackled, and they go beyond limited domain tasks such as classification. In this sense, understanding the state of the art of hybrid technologies based on Deep Learning and augmented with logic based systems, is of utmost importance. As a consequence, we seek to understand and represent the current state of these technologies that are highly used in intelligent systems engineering. This work aims to provide a comprehensive view of the solutions available in the literature, within the field of applied Artificial Intelligence (AI), using technologies based on AI techniques that integrate symbolic and non-symbolic logic (in particular artificial neural networks), making them the subject of a systematic literature review (SLR). The resulting technologies are discussed and evaluated from both perspectives: symbolic and non-symbolic AI. In this work, we use the PICOC & Limits method to define the research questions and analyze the results. Out of a total of 65 candidate studies found, 24 articles (37%) relevant to this study were selected. Each study also focuses on different application domains. Conclusion: Through the analysis of the selected works throughout this review, we have seen different combinations of logical systems with some form of neural network and, although we have not found a clear architectural pattern, efforts to find a model of general purpose combining both worlds drive trends and research efforts. https://journal.iberamia.org/index.php/intartif/article/view/702Deep LearningArtificial IntelligenceLogicHybrid Model |
| spellingShingle | Pablo Negro Claudia Pons Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature Inteligencia Artificial Deep Learning Artificial Intelligence Logic Hybrid Model |
| title | Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature |
| title_full | Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature |
| title_fullStr | Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature |
| title_full_unstemmed | Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature |
| title_short | Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks: A systematic review of the literature |
| title_sort | artificial intelligence techniques based on the integration of symbolic logic and deep neural networks a systematic review of the literature |
| topic | Deep Learning Artificial Intelligence Logic Hybrid Model |
| url | https://journal.iberamia.org/index.php/intartif/article/view/702 |
| work_keys_str_mv | AT pablonegro artificialintelligencetechniquesbasedontheintegrationofsymboliclogicanddeepneuralnetworksasystematicreviewoftheliterature AT claudiapons artificialintelligencetechniquesbasedontheintegrationofsymboliclogicanddeepneuralnetworksasystematicreviewoftheliterature |