From shallow feature learning to deep learning: Benefits from the width and depth of deep architectures

Since Pearson developed principal component analysis (PCA) in 1901, feature learning (or called representation learning) has been studied for more than 100 years. During this period, many “shallow” feature learning methods have been proposed based on various learning criteria and techniques, until the popular deep learning research in recent years. In this advanced review, we describe the historical profile of the shallow feature learning research and introduce the important developments of the deep learning models. Particularly, we survey the deep architectures with benefits from the optimization of their width and depth, as these models have achieved new records in many applications, such as image classification and object detection. Finally, several interesting directions of deep learning are presented and briefly discussed.