Adding Gaussian Processes and Optimization Methods in PyMC4

My goal for GSoC 2020 is to implement, test, and maintain a higher-level API for Gaussian Processes in PyMC4 using TensorFlow and TensorFlow Probability and write tutorials/articles and notebooks explaining their usage.

My work consists of implementing Gaussian Process Modes and writing optimization methods like Newton's Method and Powell's Method to find the maximum a-posteriori of the models. My goal is also to implement at least one approximation technique when full GP modelling becomes impractical.