Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review
Name
11633_2017_Article_1054.pdf
Size
1.68 MB
Format
Adobe PDF
Checksum (MD5)
516d85e2e44887a35fa795cbc69a11aa
Author(s)
Mhaskar, Hrushikesh
Rosasco, Lorenzo
Miranda, Brando
Liao, Qianli
Poggio, Tomaso A
Date Issued
March 2017
Journal
International Journal of Automation and Computing
Publisher
Institute of Automation, Chinese Academy of Sciences
Citation
Poggio, Tomaso, Hrushikesh Mhaskar, Lorenzo Rosasco, Brando Miranda, and Qianli Liao. “Why and When Can Deep-but Not Shallow-Networks Avoid the Curse of Dimensionality: A Review.” International Journal of Automation and Computing (March 14, 2017).
Version
Author's final manuscript
Abstract
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.
MIT Department
Center for Brains, Minds and Machines at MIT
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
McGovern Institute for Brain Research at MIT
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s11633-017-1054-2
