Facebook researchers built a new neural network that can solve complex mathematical equations, even those dealing with calculus. Here's how it works.

This analog computer on a chip is useful for certain kinds of operations that CPUs are historically not efficient at, including solving differential equations.

LI KAM SHUN, CHAN WAI LEUNG, MEROMORPHIC SOLUTIONS OF HIGHER ORDER SYSTEM OF ALGEBRAIC DIFFERENTIAL EQUATIONS, Mathematica Scandinavica, Vol. 71, No. 1 (1992), pp. 105-121 ...

Two new approaches allow deep neural networks to solve entire families of partial differential equations, making it easier to model complicated systems and to do so orders of magnitude faster.

Partial differential equations can describe everything from planetary motion to plate tectonics, but they’re notoriously hard to solve.