当前位置: X-MOL 学术arXiv.cs.SC › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
SymbolicGPT: A Generative Transformer Model for Symbolic Regression
arXiv - CS - Symbolic Computation Pub Date : 2021-06-27 , DOI: arxiv-2106.14131
Mojtaba Valipour, Bowen You, Maysum Panju, Ali Ghodsi

Symbolic regression is the task of identifying a mathematical expression that best fits a provided dataset of input and output values. Due to the richness of the space of mathematical expressions, symbolic regression is generally a challenging problem. While conventional approaches based on genetic evolution algorithms have been used for decades, deep learning-based methods are relatively new and an active research area. In this work, we present SymbolicGPT, a novel transformer-based language model for symbolic regression. This model exploits the advantages of probabilistic language models like GPT, including strength in performance and flexibility. Through comprehensive experiments, we show that our model performs strongly compared to competing models with respect to the accuracy, running time, and data efficiency.

中文翻译:

SymbolicGPT:符号回归的生成变换模型

符号回归是识别最适合提供的输入和输出值数据集的数学表达式的任务。由于数学表达式空间的丰富性,符号回归通常是一个具有挑战性的问题。虽然基于遗传进化算法的传统方法已经使用了几十年,但基于深度学习的方法相对较新,并且是一个活跃的研究领域。在这项工作中,我们提出了 SymbolicGPT,一种用于符号回归的新型基于转换器的语言模型。该模型利用了 GPT 等概率语言模型的优势,包括性能和灵活性方面的优势。通过综合实验,我们表明我们的模型在准确性、运行时间和数据效率方面与竞争模型相比表现出色。
更新日期:2021-06-29
down
wechat
bug