CALT: A Library for Computer Algebra with Transformer

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kera, Hiroshi, Arakawa, Shun, Sato, Yuta
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912422591201280
author Kera, Hiroshi
Arakawa, Shun
Sato, Yuta
author_facet Kera, Hiroshi
Arakawa, Shun
Sato, Yuta
contents Recent advances in artificial intelligence have demonstrated the learnability of symbolic computation through end-to-end deep learning. Given a sufficient number of examples of symbolic expressions before and after the target computation, Transformer models - highly effective learners of sequence-to-sequence functions - can be trained to emulate the computation. This development opens up several intriguing challenges and new research directions, which require active contributions from the symbolic computation community. In this work, we introduce Computer Algebra with Transformer (CALT), a user-friendly Python library designed to help non-experts in deep learning train models for symbolic computation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_08600
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CALT: A Library for Computer Algebra with Transformer
Kera, Hiroshi
Arakawa, Shun
Sato, Yuta
Machine Learning
Symbolic Computation
Commutative Algebra
Recent advances in artificial intelligence have demonstrated the learnability of symbolic computation through end-to-end deep learning. Given a sufficient number of examples of symbolic expressions before and after the target computation, Transformer models - highly effective learners of sequence-to-sequence functions - can be trained to emulate the computation. This development opens up several intriguing challenges and new research directions, which require active contributions from the symbolic computation community. In this work, we introduce Computer Algebra with Transformer (CALT), a user-friendly Python library designed to help non-experts in deep learning train models for symbolic computation tasks.
title CALT: A Library for Computer Algebra with Transformer
topic Machine Learning
Symbolic Computation
Commutative Algebra
url https://arxiv.org/abs/2506.08600