Deep Learning for Symbolic Mathematics

TL;DR

This paper demonstrates that neural networks can effectively perform complex symbolic mathematics tasks like integration and differential equations, surpassing traditional computer algebra systems by using a novel syntax and dataset generation methods.

Contribution

The paper introduces a new syntax for representing mathematical problems and training methods for sequence-to-sequence models, enabling neural networks to excel at symbolic mathematics.

Findings

Neural networks outperform commercial CAS in symbolic tasks

Proposed dataset generation improves training effectiveness

Sequence-to-sequence models achieve high accuracy in symbolic mathematics

Abstract

Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica.