The Landscape of Modern Machine Learning: A Review of Machine, Distributed and Federated Learning

TL;DR

This paper reviews the landscape of modern machine learning, including distributed, federated, and deep learning, highlighting recent algorithms, applications, and frameworks to serve as an introductory overview.

Contribution

It provides a comprehensive high-level overview of recent advances in machine learning, especially in distributed and federated paradigms, for newcomers to the field.

Findings

Overview of latest machine learning algorithms and frameworks

Discussion of parallel distributed and federated learning techniques

Serves as an introductory guide to modern machine learning

Abstract

With the advance of the powerful heterogeneous, parallel and distributed computing systems and ever increasing immense amount of data, machine learning has become an indispensable part of cutting-edge technology, scientific research and consumer products. In this study, we present a review of modern machine and deep learning. We provide a high-level overview for the latest advanced machine learning algorithms, applications, and frameworks. Our discussion encompasses parallel distributed learning, deep learning as well as federated learning. As a result, our work serves as an introductory text to the vast field of modern machine learning.