Very Short Literature Survey From Supervised Learning To Surrogate Modeling

TL;DR

This paper surveys the evolution from traditional linear systems to modern surrogate modeling in supervised learning, highlighting recent advances enabled by increased computational power and complexity of systems.

Contribution

It introduces surrogate modeling to those familiar with supervised learning, discussing its necessity, challenges, and future prospects.

Findings

Surrogate modeling addresses complex system approximation.

Computational resources have enabled new modeling approaches.

Surrogate modeling is increasingly important in modern system analysis.

Abstract

The past century was era of linear systems. Either systems (especially industrial ones) were simple (quasi)linear or linear approximations were accurate enough. In addition, just at the ending decades of the century profusion of computing devices were available, before then due to lack of computational resources it was not easy to evaluate available nonlinear system studies. At the moment both these two conditions changed, systems are highly complex and also pervasive amount of computation strength is cheap and easy to achieve. For recent era, a new branch of supervised learning well known as surrogate modeling (meta-modeling, surface modeling) has been devised which aimed at answering new needs of modeling realm. This short literature survey is on to introduce surrogate modeling to whom is familiar with the concepts of supervised learning. Necessity, challenges and visions of the topic are considered.