Deep vs. shallow networks : An approximation theory perspective

TitleDeep vs. shallow networks : An approximation theory perspective
Publication TypeCBMM Memos
Year of Publication2016
AuthorsMhaskar, H, Poggio, T
Date Published08/2016
Abstract

The paper briefly reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation problems than shallow, one-hidden layer architectures. The paper announces new results for a non-smooth activation function – the ReLU function – used in present-day neural networks, as well as for the Gaussian networks. We propose a new definition of relative dimension to encapsulate different notions of sparsity of a function class that can possibly be exploited by deep networks but not by shallow ones to drastically reduce the complexity required for approximation and learning. 

Journal submitted version.

arXiv

arXiv:1608.03287

DSpace@MIT

http://hdl.handle.net/1721.1/103911

CBMM Memo No:  054

Research Area: 

CBMM Relationship: 

  • CBMM Funded