Declarative Design of Neural Predicates in Neuro-Symbolic Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913670358892544 |
|---|---|
| author | Hinnerichs, Tilman Manhaeve, Robin Marra, Giuseppe Dumancic, Sebastijan |
| author_facet | Hinnerichs, Tilman Manhaeve, Robin Marra, Giuseppe Dumancic, Sebastijan |
| contents | Neuro-symbolic systems (NeSy), which claim to combine the best of both learning and reasoning capabilities of artificial intelligence, are missing a core property of reasoning systems: Declarativeness. The lack of declarativeness is caused by the functional nature of neural predicates inherited from neural networks. We propose and implement a general framework for fully declarative neural predicates, which hence extends to fully declarative NeSy frameworks. We first show that the declarative extension preserves the learning and reasoning capabilities while being able to answer arbitrary queries while only being trained on a single query type. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_09521 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Declarative Design of Neural Predicates in Neuro-Symbolic Systems Hinnerichs, Tilman Manhaeve, Robin Marra, Giuseppe Dumancic, Sebastijan Artificial Intelligence Neuro-symbolic systems (NeSy), which claim to combine the best of both learning and reasoning capabilities of artificial intelligence, are missing a core property of reasoning systems: Declarativeness. The lack of declarativeness is caused by the functional nature of neural predicates inherited from neural networks. We propose and implement a general framework for fully declarative neural predicates, which hence extends to fully declarative NeSy frameworks. We first show that the declarative extension preserves the learning and reasoning capabilities while being able to answer arbitrary queries while only being trained on a single query type. |
| title | Declarative Design of Neural Predicates in Neuro-Symbolic Systems |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2405.09521 |