Why and When Can Deep-but Not Shallow-networks Avoid the Curse of Dimensionality: A Review
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 14, 2017
- Accession Number
- AD1070438
Entities
People
- Brando Miranda
- Hrushikesh Mhaskar
- Lorenzo Rosasco
- Qianli Liao
- Tomaso Poggio
Organizations
- Massachusetts Institute of Technology