The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)

12/12/2019

∙

by   Ernest Davis, et al.

∙

0

∙

share

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. However, some important categories of examples are not included in their corpus and have not been tested. Some of these categories are certainly outside the scope of their system. Overall their system is entirely dependent on pre-existing, sophisticated, software for symbolic mathematics; it does not constitute any kind of triumph of deep learning methods over symbolic methods.