论文标题
符号表达变压器：符号回归的计算机视觉方法
Symbolic Expression Transformer: A Computer Vision Approach for Symbolic Regression
论文作者
论文摘要
符号回归（SR）是一种回归分析，可以自动找到最适合数据的数学表达式。当前，SR基本上仍然依赖各种搜索策略，因此需要针对每个表达式进行样品特定的模型，这显着限制了模型的概括和效率。受人类可以根据其曲线推断数学表达的事实的启发，我们提出了符号表达变压器（Set），这是从SR的计算机视觉的角度来看，这是一个样本 - 不可能的模型。具体而言，收集的数据表示为图像，并采用图像标题模型将图像转换为符号表达式。释放了图像域中训练和测试集之间没有重叠的大规模数据集。我们的结果证明了集合的有效性，并提出了解决挑战性SR问题的基于图像的模型的有希望的方向。
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.
