The many faces of deep learning

TL;DR

This paper explores the diverse interdisciplinary perspectives on how deep learning functions, synthesizing insights from neuroscience, physics, mathematics, and computation to foster a comprehensive understanding.

Contribution

It provides a broad synthesis of various disciplinary views on deep learning, highlighting the multifaceted nature of its mechanisms and inspiring future research directions.

Findings

Multiple disciplines offer unique insights into deep learning.

Synthesizing these perspectives enriches understanding of deep learning.

Encourages interdisciplinary approaches to advance deep learning theory and applications.

Abstract

Deep learning has sparked a network of mutual interactions between different disciplines and AI. Naturally, each discipline focuses and interprets the workings of deep learning in different ways. This diversity of perspectives on deep learning, from neuroscience to statistical physics, is a rich source of inspiration that fuels novel developments in the theory and applications of machine learning. In this perspective, we collect and synthesize different intuitions scattered across several communities as for how deep learning works. In particular, we will briefly discuss the different perspectives that disciplines across mathematics, physics, computation, and neuroscience take on how deep learning does its tricks. Our discussion on each perspective is necessarily shallow due to the multiple views that had to be covered. The deepness in this case should come from putting all these faces of deep learning together in the reader's mind, so that one can look at the same problem from different angles.