Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review
Machine Learning
2017-02-07 v5
Abstract
The paper characterizes classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for their exponential advantage.
Keywords
Cite
@article{arxiv.1611.00740,
title = {Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review},
author = {Tomaso Poggio and Hrushikesh Mhaskar and Lorenzo Rosasco and Brando Miranda and Qianli Liao},
journal= {arXiv preprint arXiv:1611.00740},
year = {2017}
}