Research Interests
(for associated publications, please click
here)
Computational Finance
From Oct. 2008 onwards, I have been researching various GP and developmental GP techniques for the analysis of trends for interday and intraday stock price data. This work has lead to a number of publications and the production of a proprietary stock analysis algorithm that is currently being commercialized.
During the industry component of my postdoctoral fellowship at Memorial University, I worked with the banking compliance software company Verafin, Inc. There, I researched machine learning techniques applied to bank financial transactions to detect debit fraud and perform AML. Directly related work is not published.
Parallel Computing and General Purpose Graphics Processing Unit (GPGPU) Programming
Recent advancements in graphics processing units (GPUs) has enabled their use as programmable parallel processors capable of very high floating point performance. Dr. Banzhaf and I have used GPUs to run a parallelized version of Linear GP and applied the algorithm to heterogeneous devices (PC, video game console, and portable media device). I was co-organizer of the Computational Intelligence on Consumer Games and Graphics Hardware (CIGPU) 2009 workshop at GECCO 2009. For further details and other related studies, please visit www.gpgpgpu.com.
Developmental Systems
My Ph.D. thesis research (supervisor Dr. Malcolm Heywood) presents the Probabilistic Adaptive Mapping DGP (PAM DGP) algorithm, a new developmental implementation that provides research contributions in the areas of GPMs and coevolution. PAM DGP produces its solutions by evolving redundant mappings to emphasize appropriate members within relevant subsets of the problem’s original function set. I co-organized the Generative and Developmental Systems (GDS) Workshop at GECCO 2009.
Genetic Programming
My research into Genetic Programming began during my Master's programme with Dr. Malcolm Heywood as supervisor. We examined linearly structured individuals (bit strings) and the use of page-based crossover to establish context within the individuals. Page-based crossover involved the trading of code segments of fixed sizes, and the establishing of code context meant that reusable sub-sections of code existed within an individual. Additional studies on LGP examined the effect of biasing mutation and crossover to operate on particular sections of the individuals` genomes in other benchmark problems. Dr. Wolfgang Banzhaf and I have also investigated the theoretical and performance differences between the graphical form of Linear Genetic Programming (LGP), Cartesian Genetic Programming (CGP), and another graph-based GP alternative.
Other Real World Applications of Evolutionary Computation
I am always interested in ways of applying genetic programming and machine learning techniques to real world domains. In particular, I have investigated GA for social network analysis (SNA) of an email corpus, a GA hybrid system to address the word tagging problem in natural language processing (NLP), and the use of GP to dynamically generate innovative business logic in a semantic web context using RuleML.
Planning Systems
During a NSERC Undergraduate Student Research Assistantship (Summer 2000), a colleague Atreya Basu and I began working on improvements to the planning system "Graphplan" under the supervision of Dr. Afzal Upal. The basic Graphplan algorithm consists of two phases: forward expansion and backward solution extraction. We explored the connections between constraint satisfaction and Graphplan’s solution extraction phase and investigated various enhancements that can lead to improved planning performance. These enhancements included (1) extending the Graphplan algorithm to learn to prune future search nodes while backtracking, (2) extending the existing learning algorithms to allow them to learn heuristics to improve the quality of the plans produced by Graphplan.
Decision Theory
Dr. Stephen Maitzen of Acadia University and I worked on a controversial game theory/decision theory problem since the completion of my undergraduate degree until publication in the Journal of Theory and Decision in 2003. Newcomb’s problem supposedly involves a Chooser, who has the option of taking one or else two boxes in certain circumstances, and a Predictor, who makes a prediction of how many boxes the Chooser will take in those circumstances. We believe that the crucial concepts of “Chooser” and “Predictor” have received too little attention. Indeed, we argue, neither of those concepts can be adequately defined: each of them conceals a vicious regress, previously unnoticed, which shows that Newcomb’s problem itself is insoluble because it is ill-formed.