Features-based embedding or Feature-grounding
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915363538599936 |
|---|---|
| author | Makarevich, Piotr |
| author_facet | Makarevich, Piotr |
| contents | In everyday reasoning, when we think about a particular object, we associate it with a unique set of expected properties such as weight, size, or more abstract attributes like density or horsepower. These expectations are shaped by our prior knowledge and the conceptual categories we have formed through experience. This paper investigates how such knowledge-based structured thinking can be reproduced in deep learning models using features based embeddings. Specially, it introduces an specific approach to build feature-grounded embedding, aiming to align shareable representations of operable dictionary with interpretable domain-specific conceptual features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_22442 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Features-based embedding or Feature-grounding Makarevich, Piotr Machine Learning In everyday reasoning, when we think about a particular object, we associate it with a unique set of expected properties such as weight, size, or more abstract attributes like density or horsepower. These expectations are shaped by our prior knowledge and the conceptual categories we have formed through experience. This paper investigates how such knowledge-based structured thinking can be reproduced in deep learning models using features based embeddings. Specially, it introduces an specific approach to build feature-grounded embedding, aiming to align shareable representations of operable dictionary with interpretable domain-specific conceptual features. |
| title | Features-based embedding or Feature-grounding |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.22442 |