Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2412.06839 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929621064220672 |
|---|---|
| author | Arakawa, Naoya |
| author_facet | Arakawa, Naoya |
| contents | This report proposes a neural cognitive model for discovering regularities in event sequences. In a fluid intelligence task, the subject is required to discover regularities from relatively short-term memory of the first-seen task. Some fluid intelligence tasks require discovering regularities in event sequences. Thus, a neural network model was constructed to explain fluid intelligence or regularity discovery in event sequences with relatively short-term memory. The model was implemented and tested with delayed match-to-sample tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06839 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Neural Model of Rule Discovery with Relatively Short-Term Sequence Memory Arakawa, Naoya Machine Learning Artificial Intelligence This report proposes a neural cognitive model for discovering regularities in event sequences. In a fluid intelligence task, the subject is required to discover regularities from relatively short-term memory of the first-seen task. Some fluid intelligence tasks require discovering regularities in event sequences. Thus, a neural network model was constructed to explain fluid intelligence or regularity discovery in event sequences with relatively short-term memory. The model was implemented and tested with delayed match-to-sample tasks. |
| title | A Neural Model of Rule Discovery with Relatively Short-Term Sequence Memory |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.06839 |