Deep Learning for Symbolic Mathematics
This addresses the challenge of making neural networks effective for precise, symbolic tasks in mathematics, which could benefit researchers and engineers in computational fields.
The paper tackles the problem of applying neural networks to symbolic mathematics, specifically symbolic integration and solving differential equations, achieving results that outperform commercial Computer Algebra Systems like Matlab or Mathematica.
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.