Files in this item

FilesDescriptionFormat

application/pdf

application/pdfLIANG-THESIS-2017.pdf (917kB)
(no description provided)PDF

Description

Title:Why deep neural networks for function approximation
Author(s):Liang, Shiyu
Advisor(s):Srikant, Rayadurgam
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):Neural networks
Deep learning
Abstract:Recently there has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that, for a large class of piecewise smooth functions, the number of neurons needed by a shallow network to approximate a function is exponentially larger than the corresponding number of neurons needed by a deep network for a given degree of function approximation. First, we consider univariate functions on a bounded interval and require a neural network to achieve an approximation error of ε uniformly over the interval. We show that shallow networks (i.e., networks whose depth does not depend on ε) require Ω(poly(1/ε)) neurons while deep networks (i.e., networks whose depth grows with 1/ε) require O(polylog(1/ε)) neurons. We then extend these results to certain classes of important multivariate functions. Our results are derived for neural networks which use a combination of rectifier linear units (ReLUs) and binary step units, two of the most popular types of activation functions. Our analysis builds on a simple observation: the multiplication of two bits can be represented by a ReLU.
Issue Date:2017-12-12
Type:Text
URI:http://hdl.handle.net/2142/99417
Rights Information:Copyright 2017 Shiyu Liang
Date Available in IDEALS:2018-03-13
Date Deposited:2017-12


This item appears in the following Collection(s)

Item Statistics