The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)
This addresses symbolic mathematics for computational tools, but is incremental due to narrow applicability.
The paper tackles symbolic integration and solving differential equations using deep learning, reporting that their system outperforms Mathematica on a specific test set, though with limitations in problem scope and dataset biases.
Lample and Charton (2019) describe a system that uses deep learning technology to compute symbolic, indefinite integrals, and to find symbolic solutions to first- and second-order ordinary differential equations, when the solutions are elementary functions. They found that, over a particular test set, the system could find solutions more successfully than sophisticated packages for symbolic mathematics such as Mathematica run with a long time-out. This is an impressive accomplishment, as far as it goes. However, the system can handle only a quite limited subset of the problems that Mathematica deals with, and the test set has significant built-in biases. Therefore the claim that this outperforms Mathematica on symbolic integration needs to be very much qualified.