Deep Learning: A Critical Appraisal
This paper addresses the limitations of deep learning for researchers and practitioners aiming for broader AI goals, but it is incremental as it builds on existing critiques without introducing new methods.
The paper critically examines the progress of deep learning over five years, highlighting its successes in areas like speech and image recognition, but raises ten concerns and argues that additional techniques are needed to achieve artificial general intelligence.
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.