Function approximation by deep networks

TitleFunction approximation by deep networks
Publication TypeCBMM Memos
Year of Publication2019
AuthorsMhaskar, HN, Poggio, T
Date Published05/2019
Abstract

We show that deep networks are better than shallow networks at approximating functions that can be expressed as a composition of functions described by a directed acyclic graph, because the deep networks can be designed to have the same compositional structure, while a shallow network cannot exploit this knowledge. Thus, the blessing of compositionality mitigates the curse of dimensionality. On the other hand, a theorem called good propagation of errors allows to “lift” theorems about shallow networks to those about deep networks with an appropriate choice of norms, smoothness, etc. We illustrate this in three contexts where each channel in the deep network calculates a spherical polynomial, a non-smooth ReLU network, or another zonal function network related closely with the ReLU network.

arXiv

https://arxiv.org/pdf/1905.12882.pdf

DSpace@MIT

https://hdl.handle.net/1721.1/121183

Download:  PDF icon CBMM-Memo-098.pdf CBMM Memo No:  098

Associated Module: 

CBMM Relationship: 

  • CBMM Funded