The motivation behind Hilbert's 13th problem is often overlooked. In his original statement of the problem, he opens with: "Nomography deals with the problem of solving equations by means of drawing families of curves depending on an arbitrary parameter". The question he posed sought to identify the family of functions amenable to such graphical solvers that were essential tools of his time. While the question in its original (algebraic) form remains open to this day, in the continuous realm it turns out that there is no such thing as a truly multivariate function. In this talk, we will explain how these ideas fit into the modern deep learning framework and, ultimately, allow us to build networks that replicate the solutions operator of stochastic differential equations governing the valuation of high dimensional contingent claims.