Stable and symmetric convolutional neural network

First we present a proof that convolutional neural networks (CNNs) with max-norm regularization, max-pooling, and Relu non-linearity are stable to additive noise. Second, we explore the use of symmetric and antisymmetric filters in a baseline CNN model on digit classification, which enjoys the stability to additive noise. Experimental results indicate that the symmetric CNN outperforms the baseline model for nearly all training sizes and matches the state-of-the-art deep-net in the cases of limited training examples.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2016

Author dc:creator

• Yeh, Raymond Alexander

Contributors dc:contributor

• Do, Minh N.

• convolutional neural network
• deep learning

Statement dc:rights

• Copyright 2016 Raymond Yeh

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/92687

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F92687