Deep Learning: A Tutorial

TL;DR

This tutorial explains how deep learning uses layered transformations to extract features from high-dimensional data, combining predictive power with uncertainty quantification.

Contribution

It provides a comprehensive review of deep learning methods emphasizing their ability to handle structured high-dimensional data and integrate statistical uncertainty quantification.

Findings

Deep learning transforms data through layered semi-affine transformations.

Features extracted enable probabilistic statistical analysis.

Combines scalable prediction with uncertainty quantification.

Abstract

Our goal is to provide a review of deep learning methods which provide insight into structured high-dimensional data. Rather than using shallow additive architectures common to most statistical models, deep learning uses layers of semi-affine input transformations to provide a predictive rule. Applying these layers of transformations leads to a set of attributes (or, features) to which probabilistic statistical methods can be applied. Thus, the best of both worlds can be achieved: scalable prediction rules fortified with uncertainty quantification, where sparse regularization finds the features.