Limitations of Deep Neural Networks: a discussion of G. Marcus' critical appraisal of deep learning
This paper addresses the potential overestimation of deep learning's capabilities and the neglect of its weaknesses, which could misdirect future research efforts for the AI community.
This paper discusses Gary Marcus' critical appraisal of deep learning, examining its limitations and potential pitfalls. It aims to clarify metaphysical misconceptions held by researchers and suggest future research directions.
Deep neural networks have triggered a revolution in artificial intelligence, having been applied with great results in medical imaging, semi-autonomous vehicles, ecommerce, genetics research, speech recognition, particle physics, experimental art, economic forecasting, environmental science, industrial manufacturing, and a wide variety of applications in nearly every field. This sudden success, though, may have intoxicated the research community and blinded them to the potential pitfalls of assigning deep learning a higher status than warranted. Also, research directed at alleviating the weaknesses of deep learning may seem less attractive to scientists and engineers, who focus on the low-hanging fruit of finding more and more applications for deep learning models, thus letting short-term benefits hamper long-term scientific progress. Gary Marcus wrote a paper entitled Deep Learning: A Critical Appraisal, and here we discuss Marcus' core ideas, as well as attempt a general assessment of the subject. This study examines some of the limitations of deep neural networks, with the intention of pointing towards potential paths for future research, and of clearing up some metaphysical misconceptions, held by numerous researchers, that may misdirect them.