<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T10:30:09Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/4845" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/4845</identifier><datestamp>2017-03-21T16:39:23Z</datestamp><setSpec>com_10012_9900</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9914</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="329cffe9-d059-4fc1-84c4-7f521433528c" confidence="600">Ventresca, Mario</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2009-11-06T19:00:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2009-11-06T19:00:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2009-11-06T19:00:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2009</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/4845</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">Symmetry has been a very useful tool to researchers in various scientific fields. At its most basic,&#xd;
symmetry refers to the invariance of an object to some transformation, or set of transformations.&#xd;
Usually one searches for, and uses information concerning an existing symmetry within given data,&#xd;
structure or concept to somehow improve algorithm performance or compress the search space. &#xd;
&#xd;
This thesis examines the effects of imposing or inducing symmetry on a search space. That is, the&#xd;
question being asked is whether only existing symmetries can be useful, or whether changing&#xd;
reference to an intuition-based definition of symmetry over the evaluation function can also be of&#xd;
use. Within the context of optimization, symmetry induction as defined in this thesis will have the&#xd;
effect of equating the evaluation of a set of given objects. &#xd;
&#xd;
Group theory is employed to explore possible symmetrical structures inherent in a search space.&#xd;
Additionally, conditions when the search space can have a symmetry induced on it are examined. The&#xd;
idea of a neighborhood structure then leads to the idea of opposition-based computing which aims&#xd;
to induce a symmetry of the evaluation function. In this context, the search space can be seen as&#xd;
having a symmetry imposed on it. To be useful, it is shown that an opposite map must be defined&#xd;
such that it equates elements of the search space which have a relatively large difference in their&#xd;
respective evaluations. Using this idea a general framework for employing opposition-based ideas&#xd;
is proposed. To show the efficacy of these ideas, the framework is applied to popular computational&#xd;
intelligence algorithms within the areas of Monte Carlo optimization, estimation of distribution and&#xd;
neural network learning.&#xd;
&#xd;
The first example application focuses on simulated annealing, a popular Monte Carlo optimization&#xd;
algorithm. At a given iteration, symmetry is induced on the system by considering opposite&#xd;
neighbors. Using this technique, a temporary symmetry over the neighborhood region is induced.&#xd;
This simple algorithm is benchmarked using common real optimization problems and compared against&#xd;
traditional simulated annealing as well as a randomized version. The results highlight improvements&#xd;
in accuracy, reliability and convergence rate. An application to image thresholding further&#xd;
confirms the results. &#xd;
&#xd;
Another example application, population-based incremental learning, is rooted in estimation of&#xd;
distribution algorithms. A major problem with these techniques is a rapid loss of diversity within&#xd;
the samples after a relatively low number of iterations. The opposite sample is introduced as a&#xd;
remedy to this problem. After proving an increased diversity, a new probability update procedure is&#xd;
designed. This opposition-based version of the algorithm is benchmarked using common binary&#xd;
optimization problems which have characteristics of deceptivity and attractive basins&#xd;
characteristic of difficult real world problems. Experiments reveal improvements in diversity,&#xd;
accuracy, reliability and convergence rate over the traditional approach. Ten instances of the&#xd;
traveling salesman problem and six image thresholding problems are used to further highlight the&#xd;
improvements. &#xd;
&#xd;
Finally, gradient-based learning for feedforward neural networks is improved using opposition-based&#xd;
ideas. The opposite transfer function is presented as a simple adaptive neuron which easily allows&#xd;
for efficiently jumping in weight space. It is shown that each possible opposite network represents&#xd;
a unique input-output mapping, each having an associated effect on the numerical conditioning of&#xd;
the network. Experiments confirm the potential of opposite networks during pre- and early training&#xd;
stages. A heuristic for efficiently selecting one opposite network per epoch is presented.&#xd;
Benchmarking focuses on common classification problems and reveals improvements in accuracy,&#xd;
reliability, convergence rate and generalization ability over common backpropagation variants. To&#xd;
further show the potential, the heuristic is applied to resilient propagation where similar&#xd;
improvements are also found.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">Symmetry Induction</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">Computational Intelligence</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">Opposition-based Computing</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="program" lang="en">System Design Engineering</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Symmetry Induction in Computational Intelligence</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending" lang="en">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">Systems Design Engineering</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>