Some Approximation Bounds for Deep Networks

03/08/2018
by   Brendan McCane, et al.
0

In this paper we introduce new bounds on the approximation of functions in deep networks and in doing so introduce some new deep network architectures for function approximation. These results give some theoretical insight into the success of autoencoders and ResNets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/21/2019

Backpropagation-Friendly Eigendecomposition

Eigendecomposition (ED) is widely used in deep networks. However, the ba...
research
11/29/2019

Deep Networks with Adaptive Nyström Approximation

Recent work has focused on combining kernel methods and deep learning to...
research
11/16/2017

A Forward-Backward Approach for Visualizing Information Flow in Deep Networks

We introduce a new, systematic framework for visualizing information flo...
research
04/08/2019

On the Learnability of Deep Random Networks

In this paper we study the learnability of deep random networks from bot...
research
04/04/2019

Taming the Knight's Tour: Minimizing Turns and Crossings

We introduce two new metrics of simplicity for knight's tours: the numbe...
research
12/20/2014

Discovering Hidden Factors of Variation in Deep Networks

Deep learning has enjoyed a great deal of success because of its ability...
research
02/17/2018

An analysis of training and generalization errors in shallow and deep networks

An open problem around deep networks is the apparent absence of over-fit...

Please sign up or login with your details

Forgot password? Click here to reset