Operator learning elevates standard machine learning from approximating a function mapping points to the operator mapping functions. This is particularly important in the realm of solving PDEs where we study the operator and look at its properties. The operators that are studied the most are linear because they are the cleanest to work with, these operators include Linear Differential Operators like the Laplacian and Fourier Transform. For problems involving cardiac modeling, we deal with nonlinear operators where much of this linear theory no longer applies. Through operator learning, we hope to leverage the same approximation power that neural networks have to functions to the neural operators with general operators.