Deep Learning: A Critical Appraisal

TL;DR

This paper critically examines the rapid progress of deep learning over five years, highlighting its achievements and limitations, and argues that additional techniques are needed to achieve artificial general intelligence.

Contribution

It provides a critical appraisal of deep learning's advancements, challenges, and the necessity of integrating other methods for future progress.

Findings

Deep learning has achieved significant success in speech and image recognition.

Despite progress, deep learning faces fundamental limitations and concerns.

Supplementing deep learning with other techniques is necessary for artificial general intelligence.

Abstract

Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now classic (2012) deep network model of Imagenet. What has the field discovered in the five subsequent years? Against a background of considerable progress in areas such as speech recognition, image recognition, and game playing, and considerable enthusiasm in the popular press, I present ten concerns for deep learning, and suggest that deep learning must be supplemented by other techniques if we are to reach artificial general intelligence.