Deep Symbolic Regression for Recurrent Sequences

Abstract

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. $bessel0(x)\approx \frac{\sin (x)+\cos (x)}{\sqrt{\pi x}}$ and $1.644934\approx {\pi }^2/6$. An interactive demonstration of our models is provided at https://symbolicregression.metademolab.com.

Cited by in corpus (11)

• Machine Learning and Deep Learning -- A review for Ecologists
• Toward Physically Plausible Data-Driven Models: A Novel Neural Network Approach to Symbolic Regression
• SYMBA: Symbolic Computation of Squared Amplitudes in High Energy Physics with Machine Learning
• Priors for symbolic regression
• Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory
• Symbolic Equation Solving via Reinforcement Learning
• Learning the Simplicity of Scattering Amplitudes
• SPINEX_ Symbolic Regression: Similarity-based Symbolic Regression with Explainable Neighbors Exploration
• Symbolic integration by integrating learning models with different strengths and weaknesses
• Grammar-based Ordinary Differential Equation Discovery
• KitBit: A New AI Model for Solving Intelligence Tests and Numerical Series