ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2201.04600
42
54

Deep Symbolic Regression for Recurrent Sequences

12 January 2022
Stéphane dÁscoli
Pierre-Alexandre Kamienny
Guillaume Lample
Franccois Charton
ArXivPDFHTML
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)≈sin⁡(x)+cos⁡(x)πx\operatorname{bessel0}(x)\approx \frac{\sin(x)+\cos(x)}{\sqrt{\pi x}}bessel0(x)≈πx​sin(x)+cos(x)​ and 1.644934≈π2/61.644934\approx \pi^2/61.644934≈π2/6. An interactive demonstration of our models is provided at https://symbolicregression.metademolab.com.

View on arXiv
Comments on this paper