The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional networks represent an important special case of these conditions, though weight sharing is not the main reason for their exponential advantage. Implications of a few key theorems are discussed, together with new results, open problems and conjectures.
CITATION STYLE
Poggio, T., Mhaskar, H., Rosasco, L., Miranda, B., & Liao, Q. (2017, October 1). Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review. International Journal of Automation and Computing. Chinese Academy of Sciences. https://doi.org/10.1007/s11633-017-1054-2
Mendeley helps you to discover research relevant for your work.