Deep vs. shallow networks : An approximation theory perspective
Author(s)Mhaskar, Hrushikesh; Poggio, Tomaso
MetadataShow full item record
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.
Center for Brains, Minds and Machines (CBMM), arXiv
CBMM Memo Series;054
hierarchical architectures, Deep Convolutional Neural Networks, ReLU function, Gaussian networks
The following license files are associated with this item: