Files in this item



application/pdfYEH-THESIS-2016.pdf (624kB)
(no description provided)PDF


Title:Stable and symmetric convolutional neural network
Author(s):Yeh, Raymond Alexander
Advisor(s):Do, Minh N.
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):convolutional neural network
deep learning
Abstract: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.
Issue Date:2016-04-26
Rights Information:Copyright 2016 Raymond Yeh
Date Available in IDEALS:2016-11-10
Date Deposited:2016-08

This item appears in the following Collection(s)

Item Statistics