Sufficiently Deep Supervised Learning in High-Dimensions & Fast Prediction, with Applications

The research is dedicated to the development of a novel method for a fast and robust prediction of a parameter that is essential to a system such that it is related to other random variable(s) (r.v.) that either affects the system or being affected by the system. Here, the term, "robust" implies as reliability

which is desired within the on-going 3rd wave of the developmental stage of Machine Learning. Let the system variable be denoted as X and the associated observable as Y . Either, or both these r.v.s could be higher-dimensional as well rather than being just scalars. In this Ph.D, I will learn the functional

relationship f(.) between X and Y i.e. Y = f(X) to predict the values of X at which a (noisy) test datum on Y is observed, where the prediction will be fast and reliable.