arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.11798cs.CVcs.AI
收藏

Symbolic Expression Transformer:一种符号回归的计算机视觉方法

Symbolic Expression Transformer: A Computer Vision Approach for Symbolic Regression

Shanghai Jiao Tong University(上海交通大学)

Jiachen Li, Ye Yuan, Hong-Bin Shen

摘要:

符号回归(SR)是一种回归分析,用于自动找到最适合数据的数学表达式。目前,SR仍然基本上依赖于各种搜索策略,因此需要针对每个表达式优化样本特定的模型,这大大限制了模型的泛化和效率。受人类可以根据数学表达式的曲线推断数学表达式的启发,从计算机视觉的角度提出了一种与样本无关的符号表达式Transformer(SET)模型。发布了图像域中训练集和测试集之间没有重叠的大规模数据集。我们的研究结果证明了SET的有效性,并提出了基于图像的模型解决具有挑战性的SR问题的有前途的方向。

英文摘要:

Symbolic Regression (SR) is a type of regression analysis to automatically find the mathematical expression that best fits the data. Currently, SR still basically relies on various searching strategies so that a sample-specific model is required to be optimized for every expression, which significantly limits the model's generalization and efficiency. Inspired by the fact that human beings can infer a mathematical expression based on the curve of it, we propose Symbolic Expression Transformer (SET), a sample-agnostic model from the perspective of computer vision for SR. Specifically, the collected data is represented as images and an image caption model is employed for translating images to symbolic expressions. A large-scale dataset without overlap between training and testing sets in the image domain is released. Our results demonstrate the effectiveness of SET and suggest the promising direction of image-based model for solving the challenging SR problem.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑