论文标题
复发序列的深符号回归
Deep Symbolic Regression for Recurrent Sequences
论文作者
论文摘要
符号回归，即从对其值的观察中预测功能，是众所周知的一项挑战。在本文中，我们训练变形金刚推断整数或浮子的功能或复发关系序列，这是人类智商测试中的典型任务，在机器学习文献中几乎没有解决。我们在OEIS序列的子集上评估了整数模型，并表明它的表现优于内置的Mathematica函数，用于复发预测。我们还证明，我们的浮点模型能够产生量像库外功能和常数的信息近似值，例如$ \ operatatorName {bessel0}（x）\大约\ frac {\ sin（x）+\ cos（x）} {\ sqrt {πx}} $和$ 1.644934 \ lib ofist^2/6 $。在https://symbolicrecress.metademolab.com上提供了我们模型的互动演示。
Symbolic regression, i.e. predicting a function from the observation of its values, is well-known to be a challenging task. In this paper, we train Transformers to infer the function or recurrence relation underlying sequences of integers or floats, a typical task in human IQ tests which has hardly been tackled in the machine learning literature. We evaluate our integer model on a subset of OEIS sequences, and show that it outperforms built-in Mathematica functions for recurrence prediction. We also demonstrate that our float model is able to yield informative approximations of out-of-vocabulary functions and constants, e.g. $\operatorname{bessel0}(x)\approx \frac{\sin(x)+\cos(x)}{\sqrt{πx}}$ and $1.644934\approx π^2/6$. An interactive demonstration of our models is provided at https://symbolicregression.metademolab.com.
