Constrained Neural Networks for Interpretable Heuristic Creation to Optimise Computer Algebra Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913331321765888 |
|---|---|
| author | Florescu, Dorian England, Matthew |
| author_facet | Florescu, Dorian England, Matthew |
| contents | We present a new methodology for utilising machine learning technology in symbolic computation research. We explain how a well known human-designed heuristic to make the choice of variable ordering in cylindrical algebraic decomposition may be represented as a constrained neural network. This allows us to then use machine learning methods to further optimise the heuristic, leading to new networks of similar size, representing new heuristics of similar complexity as the original human-designed one. We present this as a form of ante-hoc explainability for use in computer algebra development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17508 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Constrained Neural Networks for Interpretable Heuristic Creation to Optimise Computer Algebra Systems Florescu, Dorian England, Matthew Symbolic Computation Machine Learning 68W30, 68T05, 03C10 I.2.6; I.1.0 We present a new methodology for utilising machine learning technology in symbolic computation research. We explain how a well known human-designed heuristic to make the choice of variable ordering in cylindrical algebraic decomposition may be represented as a constrained neural network. This allows us to then use machine learning methods to further optimise the heuristic, leading to new networks of similar size, representing new heuristics of similar complexity as the original human-designed one. We present this as a form of ante-hoc explainability for use in computer algebra development. |
| title | Constrained Neural Networks for Interpretable Heuristic Creation to Optimise Computer Algebra Systems |
| topic | Symbolic Computation Machine Learning 68W30, 68T05, 03C10 I.2.6; I.1.0 |
| url | https://arxiv.org/abs/2404.17508 |