Deep Learning: A Tutorial
This is an incremental review paper for researchers and practitioners in machine learning, summarizing existing deep learning techniques without introducing new methods.
The paper tackles the challenge of analyzing structured high-dimensional data by reviewing deep learning methods that combine scalable prediction rules with uncertainty quantification, achieving improved predictive performance through sparse regularization.
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.