Learning Closed Signal Flow Graphs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929403951316992 |
|---|---|
| author | Piotrovskaya, Ekaterina Lobski, Leo Zanasi, Fabio |
| author_facet | Piotrovskaya, Ekaterina Lobski, Leo Zanasi, Fabio |
| contents | We develop a learning algorithm for closed signal flow graphs - a graphical model of signal transducers. The algorithm relies on the correspondence between closed signal flow graphs and weighted finite automata on a singleton alphabet. We demonstrate that this procedure results in a genuine reduction of complexity: our algorithm fares better than existing learning algorithms for weighted automata restricted to the case of a singleton alphabet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00245 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Closed Signal Flow Graphs Piotrovskaya, Ekaterina Lobski, Leo Zanasi, Fabio Logic in Computer Science Machine Learning 68Q45 F.1.1; D.3.1 We develop a learning algorithm for closed signal flow graphs - a graphical model of signal transducers. The algorithm relies on the correspondence between closed signal flow graphs and weighted finite automata on a singleton alphabet. We demonstrate that this procedure results in a genuine reduction of complexity: our algorithm fares better than existing learning algorithms for weighted automata restricted to the case of a singleton alphabet. |
| title | Learning Closed Signal Flow Graphs |
| topic | Logic in Computer Science Machine Learning 68Q45 F.1.1; D.3.1 |
| url | https://arxiv.org/abs/2407.00245 |