CityU Institutional Repository >
3_CityU Electronic Theses and Dissertations >
ETD - Dept. of Electronic Engineering >
EE - Master of Philosophy >
Please use this identifier to cite or link to this item:
|Title: ||Regularizer design for fault tolerant neural networks|
|Other Titles: ||She ji yong yu rong cuo shen jing wang luo de zheng ze qi|
|Authors: ||Mak, Shue Kwan ( 麥澍堃)|
|Department: ||Department of Electronic Engineering|
|Degree: ||Master of Philosophy|
|Issue Date: ||2011|
|Publisher: ||City University of Hong Kong|
|Subjects: ||Neural networks (Computer science)|
|Notes: ||CityU Call Number: QA76.87 .M34 2011|
vii, 66 leaves : ill. 30 cm.
Thesis (M.Phil.)--City University of Hong Kong, 2011.
Includes bibliographical references (leaves 62-66)
|Abstract: ||Fault tolerance is an important issue in neural networks. While there are some fault
tolerant training algorithms, they often have their own tradeoffs. Recently, an open
node fault regularizer (ONFR) was proposed to obtain fault tolerant radial basis function
(RBF) networks. This regularization technique is computationally simple and
does not alter the network structure. Following similar concept, this thesis introduces
an ONFR for multilayer feedforward networks (MFN). With the linearization technique,
the training objective function can be decomposed into two simple terms, the
training error and the ONFR. Gradient based learning methods can then be employed
to obtain fault tolerant networks.
Notice that the goal of training a fault tolerant network is to minimize the generalization
error over faulty networks, however, the current ONFRs minimizes the
training error over faulty networks only. This thesis thus presents a design strategy
for the ONFR to optimize the generalization ability for faulty RBF networks. A mean
prediction error (MPE) formula, which consists of the training error and the trained
weight, is developed to predict the generalization ability of a faulty RBF network.
Thus, we can optimize the ONFR parameter in terms of the generalization ability
over faulty networks efficiently. The formula can also be used to select an appropriate
|Online Catalog Link: ||http://lib.cityu.edu.hk/record=b4086713|
|Appears in Collections:||EE - Master of Philosophy |
Items in CityU IR are protected by copyright, with all rights reserved, unless otherwise indicated.