Contact a member of the group to request a publication.
All papers tagged with an ACM icon are downloadable at no cost by using the link from this page.
Table of Contents
- Journals and Book Chapters
- Posters (2013)
- Journals and Book Chapters
- Journals and Book Chapters
- Journal Articles
- Conference Papers
- Bibtex entries for recent publications
- Papers on Meta Optimization
- More Publications (historical list)
- Abstracts of Recent Publications
Dr. O'Reilly consistently publishes under the name Una-May O'Reilly with the abbreviation U.M. O'Reilly. However there are numerous citations of her papers which are inconsistent in citing her name. Popular errors (try to spot them!) are Una May O'Reilly, Una-May O Reilly, OReilly, Una M, U-M or U.-M. or U-M. with many combinations of the preceding errors which mangle the hyphen or apostrophe. We have even found that different fonts have different apostrophes so that two equivalent citations are not attributed to the same paper!
A few sources have incomplete but somewhat extensive lists of my publications:
- Acm digital library entry for Una-May O'Reilly (note, not Una May May O Reilly)
- GP bibliography when I'm listed as Una-May O'Reilly
- DBLB of Uni. Trier
- The Max Problem Revisited: The Importance of Mutation in Genetic Programming, Timo Koetzing, Andrew M. Sutton, Frank Neumann and Una-May O'Reilly, to appear, Theoretical Computer Science, special issue on Genetic and Evolutionary Computation.
- Techniques for Accurate Wind Resource Estimation by Modeling Statistical Dependency K. Veeramachaneni, Xiang Ye, U.M. O'Reilly, Ch 10, pp 303-330 in Computational Intelligent Data Analysis for Sustainable Development, Editors: Ting Yu, Nitesh Chawla, Simeon Simoff, Chapman & Hall/CRC Data Mining and Knowledge Discovery Series, Taylor & Francis, 2013. ISBN 9781439895948. Link to Book.
- Genetic Programming, James McDermott and Una-May O'Reilly, In the Handbook of Computational Intelligence (forthcoming), Topic Editors: Dr. F. Neumann and Dr. K Witt, Editors in Chief Prof. Janusz Kacprzyk and Prof. Witold Pedrycz.
- Better GP benchmarks: community survey results and proposals, David R. White, James McDermott, Mauro Castelli, Luca Manzoni, Brian W. Goldman, Gabriel Kronberger, Wojciech Jaśkowski, Una-May O'Reilly, Sean Luke, Genetic Programming and Evolvable Machines, Volume 14 Issue 1, March 2013, Pages 3-29. DOI: 10.1007/s10710-012-9177-2
- Maintenance of a Long Running Distributed Genetic Programming System For Solving Problems Requiring Big Data, Babak Hodjat, Erik Hemberg, Hormoz Shahrzad and Una-May O'Reilly, to appear in Genetic Programming Theory and Practice XI.
- Modeling Service Execution on Data Centers for Energy Efficiency and Quality of Service Monitoring, M. Vitali, U. O’Reilly, and K. Veeramachaneni, Special Session on Energy Efficient Systems at IEEE International Conference on Systems, Man and Cybernetics (SMC), October 13 – 16, 2013, Manchester, UK, IEEE Computer Society, pp 103-108. (pre-camera version provided)
- Introducing Graphical Models to Analyze Genetic Programming Dynamics Erik Hemberg, Constantin Berzan, Kalyan Veeramachaneni, Una-May O'Reilly FOGA XII '13 Proceedings of the twelfth workshop on Foundations of genetic algorithms XII, 2013
- Large Scale Island Model CMA-ES for High Dimensional Problems, Dennis Wilson, Kalyan Veeramachaneni, and Una-May O'Reilly, EVOPAR track, Applications of Evolutionary Computation, Lecture Notes in Computer Science Volume 7835, 2013, pp 519-528.
- Cloud Driven Design of a Distributed Genetic Programming Platform, Owen Derby, Kalyan Veeramachaneni, and Una-May O'Reilly, EVOPAR track, Applications of Evolutionary Computation, Lecture Notes in Computer Science Volume 7835, 2013, pp 509-518.
- Learning regression ensembles with genetic programming at scale, Kalyan Veeramachaneni, Owen Derby, Dylan Sherry, Una-May O'Reilly, GECCO '13, Proceeding of the fifteenth annual conference on Genetic and evolutionary computation conference, 2013
- On Learning to Generate Wind Farm Layouts, Dennis Wilson, Emmanuel Awa, Sylvain Cussat-Blanc, Kalyan Veeramachaneni, Una-May O'Reilly, GECCO '13, Proceeding of the fifteenth annual conference on Genetic and evolutionary computation conference, 2013
- Modeling Tax Evasion with Genetic Algorithms, Geoffrey Warner, Sanith Wijesinghe , Uma Marques, Una-May O'Reilly, Erik Hemberg, Osama Badar, Shadow 2013, Munster.
- Building MultiClass Nonlinear Classifiers with GPUs, Ignacio Arnaldo, Kalyan Veeramachaneni and Una-May O'Reilly, 2014 NIPS Workshop on Big Learning. Workshop papers.
- beatDB : A Large Scale Waveform Feature Repository, Franck Dernoncourt,, Kalyan Veeramachaneni and Una-May O'Reilly, MLCDA@NIPS 2013 : Machine Learning for Clinical Data Analysis and Healthcare.
- MoocViz: A Large Scale, Open Access, Collaborative Data Analytics Framework for MOOCs , Franck Dernoncourt,,Choung Do, Sherif Halawa, Una-May O'Reilly, Colin Taylor, Kalyan Veeramachaneni and Sherwin Wu, DDE@NIPS 2013: Data Directed Education. Workshop website.
- Analyzing Millions of Submissions to Help MOOC instructors Understand Problem Solving , Fang Han, Kalyan Veeramachaneni and Una-May O'Reilly, DDE@NIPS 2013: Data Directed Education. Workshop website.
- Copula-Based Wind Resource Assessment, Kalyan Veeramachaneni, Teasha Feldman-Fitzthum, Una-May O’Reilly, Alfredo Cuesta-Infante, Machine Learning for Sustainability Workshop@NIPS 2013.website
- Efficient Training Set Use For Blood Pressure Prediction in a Large Scale Learning Classifier System, Erik Hemberg, Kalyan Veeramachaneni, Franck Dernoncourt, Mark Wagy and Una-May O'Reilly, Sixteenth International Workshop on Learning Classifiers Systems.
- Learning Blood Pressure Behavior from Large Physiological Waveform Repositories, Alexander Waldin, Kalyan Veeramachaneni, Una-May O'Reilly, ICML Workshop on Healthcare 2013.
- MOOCdb: Developing Data Standards for MOOC Datascience, Kalyan Veeramachaneeni, Zachary A. Pardos, Una-May O'Reilly, MOOCShop at Artificial Intelligence in Education, 2013. Also available from website of workshop, here.
- Imprecise Selection and Fitness Approximation in a Large-Scale Evolutionary Rule Based System for Blood Pressure Prediction, Erik Hemberg, Kalyan Veeramachaneni, Franck Dernoncourt, Mark Wagy and Una-May O'Reilly, GECCO 2013, Amsterdam, The Netherlands, May 2013.
- Large-scale Consensus Clustering and Data Ownership Considerations for Medical Applications, Chidube Ezeozue, S.M, thesis, MIT Dept of EECS, 2013. Advisors: Una-May O'Reilly, Kalyan Veeramachaneni.
- FlexGP: A Scalable System for Factored Learning in the Cloud, Owen Derby, M.Eng, thesis, completed in MIT Dept of EECS, 2013. Advisors: Una-May O'Reilly, Kalyan Veeramachaneni.
- Learning Blood Pressure Behavior from Large Blood Pressure Waverform Repositories and Building Predictive Models, Alexander Waldin, Masters Thesis, ETH-Zurich, 2013. Advisors: Una-May O'Reilly, Kalyan Veeramachaneni.
- FlexGP 2.0: Multiple Levels of Parallelism in Distributed Machine Learning via Genetic Programming. Dylan Sherry, 2013. Download
- Evolutionary and generative music informs music HCI—and vice versa, James McDermott, Dylan Sherry, and Una-May O’Reilly. In Kate Wilkie, Simon Holland, Paul Mulholland, and Allan Seago, editors, Music Interaction. Springer, 2012. forthcoming.
- EC-Star: A Massive-Scale, Hub and Spoke, Distributed Genetic Programming System, Babak Hodjat, Mark Wagy and Una-May O'Reilly. To appear in Proceedings of Genetic Programming X: From Theory to Practice, Kluwer, 2012. pre-camera version
- FlexGP.py: Prototyping Flexibly-Scaled, Flexibly-Factored Genetic Programming for the Cloud. James McDermott, Kalyan Veeramachaneni and Una-May O'Reilly. Proceedings of Genetic Programming X: From Theory to Practice, Kluwer, 2012. pre-camera version
- P. Fazenda, J. McDermott, and U.M. O’Reilly. A library to run evolutionary algorithms in the cloud using MapReduce. In EvoApplications 2012: EvoCOMNET, EvoCOMPLEX, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoNUM, EvoPAR, EvoRISK, EvoSTIM, EvoSTOC, LNCS, Vol. 7248, pp. 416-425, Springer Verlag, 11-13 April 2012. (this paper was in the EvoPAR conference)
- D. Sherry, K. Veeramachaneni, J. McDermott, and U.M. O’Reilly. Flex- GP: Genetic programming on the cloud. In EvoApplications 2012: EvoCOMNET, EvoCOMPLEX, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoNUM, EvoPAR, EvoRISK, EvoSTIM, EvoSTOC, LNCS, Vol. 7248, pp. 477-486, Springer Verlag, 11-13 April 2012. (this paper was in the EvoPAR conference. It was awarded Best Paper.)
- Maciej Pacula and Jason Ansel and Saman Amarasinghe and Una-May O'Reilly. Hyperparameter Tuning in Bandit-Based Adaptive Operator Selection, Applications of Evolutionary Computing, EvoApplications2012: EvoCOMNET, EvoCOMPLEX, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoNUM, EvoPAR, EvoRISK, EvoSTIM, EvoSTOC, LNCS, Vol. 7248, pp. 71-80, Springer Verlag, 11-13 April 2012.
- James McDermott, David R. White, Sean Luke, Luca Manzoni, Mauro Castelli, Leonardo Vanneschi, Wojciech Jaskowski, Krzysztof Krawiec, Robin Harper, Kenneth De Jong, and Una-May O’Reilly. Genetic programming needs better benchmarks. In Proceedings of GECCO 2012, Philadelphia, 2012. ACM.E. Hemberg, K. Veeramachaneni, J. McDermott, C. Berzan, and U-M. O’Reilly. An investigation of local patterns for estimation of distribution genetic programming.. In Proceedings of GECCO 2012, Philadelphia, 2012. ACM.Timo Kotzing, Andrew M. Sutton, Frank Neumann and Una-May O'Reilly, The max problem revisited: the importance of mutation in genetic programming, in GECCO '12 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference, 2012.
- Kalyan Veeramachaneni, Markus Wagner, Una-May O'Reilly and Frank Neumann, Optimizing Energy Output and Layout Costs for Large Wind Farms using Particle Swarm Optimization, to appear in 2012 IEEE Congress on Evolutionary Computation.
- Kyle Harrington, Lee Spector, Jordan Pollack and Una-May O'Reilly, Autoconstructive Evolution for Structural Problems, 2nd Workshop on Evolutionary Computation for the Automated Design of Algorithms, in Companion Volume of GECCO 2012, Philadelphia, 2012.Erik Hemberg, Kalyan Veeramachaneni and Una-May O'Reilly, Graphical Models and What They Reveal about Genetic Programming', Symbolic Regression and Modelling Workshop, GECCO 2012, Philadelphia, 2012. Presentation as PDF
- Computational Complexity Analysis of Genetic Programming - Initial Results and Future Directions, Frank Neumann, Una-May O’Reilly and Markus Wagner, Proceedings of Genetic Programming IX: From Theory to Practice, Editors: Jason Moore, Rick Riolo, Katya Vladaislavleva, Kluwer Press. abstract
- Baseline Genetic Programming Symbolic Regression on Benchmarks for Sensory Evaluation Modeling, Pierre-Luc Noel, Kalyan Veeramachaneni, and Una-May O’Reilly, Proceedings of Genetic Programming IX: From Theory to Practice, Editors: Jason Moore, Rick Riolo, Katya Vladaislavleva, Springer Press. preprint as pdf, Abstract
- Feature extraction from optimization samples via ensemble based symbolic regression, Kalyan Veeramachaneni, Ekaterina Vladislavleva, Una-May O’Reilly, forthcoming in Annals of Mathematics and Artificial Intelligence, Springer. Online-first preprint as pdf, Abstract 2011, Volume 61, Number 2, Pages 105-123
- Knowledge Mining Sensory Evaluation Data with Genetic Programming, Statistical Techniques, and Swarm Optimization, Kalyan Veeramachaneni, Ekaterina Vladislavleva, Una-May O’Reilly, Genetic Programming and Evolvable Machines 3(1), pp. 103-133, March 2012. .
- Computational complexity analysis of simple genetic programming on two problems modeling isolated program semantics, Greg Durrett, Frank Neumann, Una-May O'Reilly, Foundations of Genetic Algorithms (FOGA), 2011. abstract
- How Far Is It From Here to There? A Distance that is Coherent with GP Operators, James McDermott, Leonardo Vanneschi, Kalyan Veeramachaneni, Una-May O'Reilly, Proceedings of 2011 European Conference on Genetic Programming (EuroGP), Springer LNCS.
- An executable graph representation for evolutionary generative music, James McDermott, Una-May O'Reilly, Evolutionary Music and Art Track, 2011 Genetic and Evolutionary Computation Conference (GECCO 2011), Dublin, Ireland. July, 2011.
- An efficient evolutionary algorithm for solving incrementally structured problems, Jason Ansel, Maciej Pacula, Saman Amarasinghe, Una-May O'Reilly, Real World Applications track of Genetic and Evolutionary Computation Conference (GECCO 2011), Dublin, Ireland. July, 2011.
- Optimizing the Layout of 1000 Wind Turbines, Markus Wagner, Kalyan Veeramachaneni, Frank Neumann, Una-May O'Reilly, in the Scientific Proceedings of the 2011 meeting of the European Wind Energy Association (EWEA 2011). pdf
- Creative transformations: How generative and evolutionary music can inform music HCI, James McDermott, Dylan Sherry, and Una-May O’Reilly, to appear In Proceedings of BCS HCI 2011 Workshop – When Words Fail: What Can Music Interaction tel l us about HCI? British Computer Society, 2011.
- Evolutionary Approaches for Wind Resource Assessment , Kalyan Veeramachaneni, Una-May O'Reilly, in the Proceedings of 2011 annual meeting of American Wind Energy Association, (WINDPOWER 2011). pdf
Hogs and Slackers: Using Operations Balance in a Genetic Algorithm to Optimize Sparse Algebra Computation on Distributed Architectures. Una-May O'Reilly, Eric Robinson, Sanjeev Mohindra, Julie Mullen, Nadya Bliss, Parallel Computing, Volume 36, Issues 10-11, October-November 2010, Pages 635-644 Special Issue on Parallel Architectures and Bioinspired Algorithms.Knowledge mining with genetic programming methods for variable selection in flavor design. Katya Vladislavleva, Kalyan Veeramachaneni, Matt Burland, Jason Parcon, Una-May O'Reilly, Genetic and Evolutionary Computation Conference (GECCO), pp. 941-948, ACM, 2010. Genetic programming track.Evolutionary optimization of flavors. Kalyan Veeramachaneni, Katya Vladislavleva, Matt Burland, Jason Parcon, Una-May O'Reilly, Genetic and Evolutionary Computation Conference (GECCO), pp. 1291-1298, ACM, 2010. Real World Applications track.
Feature Extraction from Optimization Data via DataModeler’s Ensemble Symbolic Regression. Kalyan Veeramachaneni, Katya Vladislavleva, Una-May O' Reilly, Learning and Intelligent Optimization (LION), Lecture Notes in Computer Science, Vol. 6073, pp. 251-265, Springer, 2010. (pdf)
Learning a Lot from Only a Little: Genetic Programming for Panel Segmentation on Sparse Sensory Evaluation Data. Katya Vladislavleva, Kalyan Veeramachaneni, Una-May O' Reilly, Matt Burland, Jason Parcon, Proceedings of the 13th European Conference on Genetic Programming, EuroGP 2010, LNCS, Vol. 6021, pp. 244-255, Springer, 7-9 April 2010. (pdf)
A Genetic Algorithm to Minimize Chromatic Entropy. Greg Durett, Muriel Medard, and Una-May O'Reilly, 10th European Conference on Evolutionary Computation in Combinatorial Optimisation (EvoCOP), Lecture Notes in Computer Science, Vol. 6022, pp. 59-70, Springer, 7-9 April 2010.. (pdf)
Network Coding in Optical Networks with O/E/O Based Wavelength Conversion. Ramanthan S. Thinniyam, Minkyu Kim, Muriel Medard, Una-May O'Reilly, Poster presented at Optical Fiber Communication Conference OFC 2010.(pdf)Genetic programming for quantitative stock selection. Becker, Ying L. and Una-May O'Reilly, Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC 2009.
Multi-objective Optimization of Sparse Array Computations. Una-May O'Reilly, Nadya Travinin Bliss, Sanjeev Mohindra, Julie Mullen, Eric Robinson, Proceedings of 2009 Workshop on High Performance Embedded Computing, (HPEC 2009). (paper as pdf and PPT presentation as pdf)
Genetic Programming: Theory and Practice VI, Terence Soule, Rick L. Riolo and Una-May O'Reilly (editors) Springer, 2009.
An Evolutionary Approach to Inter-session Network Coding. Kim Minkyu, Médard Mureil, O’Reilly Una-May, Traskov Danial, In Proceedings of IEEE INFOCOM 2009, April 2009.
Integrating Network Coding Into Heterogeneous Wireless Networks. Minkyu Kim, Muriel Medard, Una-May O'Reilly, MILComm 08. IEEE Computer Society.
Constrained Genetic-Programming to Minimize Overfitting in the Stock Selection. Minkyu Kim, Ying L. Becker, Peng Fei, and Una-May O'Reilly, Genetic Programming: Theory and Practice VI, Springer, 2008.
Performance Modeling and Mapping of Sparse Computations. Nadya T. Bliss, Sanjeev Mohindra, Una-May O'Reilly, DOD HPCMP (High Performance Computing Modernization Program) Users Group Conference 2008, IEEE Computer Society. (pdf Δ)
Analysis and Mapping of Sparse Matrix Computations. Nadya Travinin Bliss, Sanjeev Mohindra, V. Aggarwal, U.M. O'Reilly, Proceedings of High Performance Embedded Computing, (HPEC 2007).
Simulation-based reusable posynomial models for MOS transistor parameters. Varun Aggarwal, Una-May O'Reilly, Proceedings of the Conference on Design, Automation and Test in Europe (Nice, France, April 16 - 20, 2007), DATE '07, ACM Press, New York, NY, pp. 69-74.COSMO: a correlation sensitive mutation operator for multi-objective optimization. Varun Aggarwal, Una-May O'Reilly, Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation (London, England, July 07 - 11, 2007), GECCO '07, ACM Press, New York, NY, pp. 741-748
Evolutionary Approaches to Minimizing Network Coding Resources. Minkyu Kim, Muriel Médard, Varun Aggarwal, Una-May O'Reilly, Wonsik Kim, Chang Wook Ahn, Michelle Effros, 26th Annual IEEE Conference on Computer Communications (INFOCOM 2007).
Genetic Representations for Evolutionary Minimization of Network Coding Resources. Minkyu Kim, Varun Aggarwal, Una-May O'Reilly, Muriel Médard, Wonsik Kim, 4th European Workshop on the Application of Nature-Inspired Techniques to Telecommunication Networks and Other Connected Systems (EvoCOMNET 2007), Springer, 2007.A doubly distributed genetic algorithm for network coding. Minkyu Kim, Varun Aggarwal, Una-May O'Reilly, and Muriel Médard, Proceedings of the 9th Annual Conference on Genetic and Evolutionary Computation (London, England, July 07 - 11, 2007), GECCO '07, ACM Press, New York, NY, pp. 1272-1279.
On the Coding-Link Cost Tradeoff in Multicast Network Coding. Minkyu Kim, Muriel Médard, Varun Aggarwal, and Una-May O'Reilly, to appear at 2007 Military Communications Conference (MILCOM 2007), October 2007, Orlando, FL.
On the "Evolvable Hardware" Approach to Electronic Design Invention. Varun Aggarwal, Karl Berggren, Una-May O'Reilly, Evolvable and Adaptive Hardware, 2007, WEAH 2007, IEEE Workshop on 1-5 April 2007, pp. 46 - 54.
Integrating Generative Growth and Evolutionary Computation for Form Exploration. U. M. O'Reilly and M. Hemberg, Genetic Programming and Evolvable Machines, (2007), 8:163-186.
Design of Posynomial Models for Mosfets: Symbolic Regression Using Genetic Algorithms. Varun Aggarwal, Una-May O'Reilly, Genetic Programming: Theory and Practice IV, Chapter 7, 2006. (pdf)
GRACE: Generative Robust Analog Circuit Design. Michael A. Terry, Jonathan Marcus, Matthew Farrell, Varun Aggarwal, Una-May O'Reilly, Proceedings of Applications of Evolutionary Computing, EvoWorkshops 2006: (EvoHOT), Lecture Notes in Computer Science 3907, pp 332-343, Springer Verlag. (pdf)
A Self-Tuning Analog Proportional-Integral-Derivative (PID) Controller. Varun Aggarwal, Meng Mao and Una-May O'Reilly, Adaptive Hardware Systems, 2006, IEEE Press. (pdf)Filter approximation using explicit time and frequency domain specifications.
Varun Aggarwal, Wesley O. Jin and Una-May O'Reilly, GECCO 2006, pp. 753 - 760 Evolutionary Hardware track. (Nominated for BEST PAPER AWARD)
Use this link to get to Una-May O'Reilly's author page on the ACM Digital Library. There are bibtex entries for papers there. Or...
Use this webpage to search for any publication by Dr. O'Reilly. An orange scissors icon will appear when you hover your mouse just to the left of the word "Search" above the query box. Clicking on it will show the bibtex entry. You will have to use the back arrow in your web browser to return to this wiki page. Back to 2011 Publications
(included by popular request)Meta optimization: improving compiler heuristics with machine learning, M. Stephenson, U.M. O'Reilly, M.C. Martin, and S. Amarasinghe, Proceedings of the ACM SIGPLAN '03 Conference on Programming Language Design and Implementation, San Diego, California, June, 2003.
Genetic Programming Applied to Compiler Heuristic Optimization, M. Stephenson, U.M. O'Reilly, M.C. Martin, and S. Amarasinghe, Proceedings of the 6th European Conference on Genetic Programming, C. Ryan, T. Soule, M. Keijzer, E. Tsang, R. Poli , E. Costa (editors), LNCS Vol. 2610, Springer Verlag, 2003.
Adapting Convergent Scheduling Using Machine-Learning, D. Puppin, M. Stephenson, S. Amarasinghe, M.C. Martin, U.M. O'Reilly, 16th International Workshop on Languages and Compilers for Parallel Computing, LNCS, Springer Verlag, 2003.
A longer and more historical list of my publications.
Computational Complexity Analysis of Simple Genetic Programming On Two Problems Modeling Isolated Program Semantics, Abstract: Analyzing the computational complexity of evolutionary algorithms for binary search spaces has significantly increased their theoretical understanding. With this paper, we start the computational complexity analysis of genetic programming. We set up several simplified genetic programming algorithms and analyze them on two separable model problems, ORDER and MAJORITY, each of which captures an important facet of typical genetic programming problems. Both analyses give first rigorous insights on aspects of genetic programming design, highlighting in particular the impact of accepting or rejecting neutral moves the importance of a local mutation operator. Back to 2011 Publications
Feature extraction from optimization samples via ensemble based symbolic regression, Abstract: We demonstrate a means of knowledge discovery through feature extraction that exploits the search history of a search-based optimization run. We regress a symbolic model ensemble from optimization run search points and their objective scores. The frequency of a variable in the models of the ensemble indicates to what the extent it is an influential feature. Our demonstration uses a genetic programming symbolic regression software package that is designed to be off-the-shelf . By default, the only parameter needed in order to evolve a suite of models is how long the user is willing to wait. Then the user can easily specify which models should go forward in terms of sufficient accuracy and complexity. For illustration purposes, we consider a sequencing heuristic used to chain remote sensors from one to the next: place the most reliable sensor last . The heuristic is derived based on the mathematical form of the optimization objective function which places emphasis on the decision variable pertaining to the last sensor. Feature extraction on optimized sensor sequences demonstrates that the heuristic is usually effective though it is not always trustworthy. This is consistent with knowledge in sensor processing. Back to 2011 Publications
Computational Complexity Analysis of Genetic Programming - Initial Results and Future Directions, Abstract: The computational complexity analysis of evolutionary algorithms working on binary strings has significantly increased the rigorous understanding on how these types of algorithm work. Similar results on the computational complexity of genetic programming would fill an important theoretic gap. They would signiﬁcantly increase the theoretical understanding on how and why genetic programming algorithms work and indicate, in a rigorous manner, how design choices of algorithm components impact its success. We summarize initial computational complexity results for simple tree-based genetic programming and point out directions for future research. Back to 2011 Publications
Benchmarking Genetic Programming Symbolic Regression for Sensory Evaluation Modeling, Abstract: We introduce hedonic modeling benchmarks for the field of sensory science evaluation. Our benchmark framework provides a general means of defining a response surface which we call a ``sensory map''. A sensory map} is described by a mathematical expression which rationalizes domain specific knowledge of the explanatory variables and their individual or higher order contribution to hedonic response. The benchmark framework supports the sensory map's so-called ground truth to be controllably distorted to mimic the human and protocol factors that obscure it. To provide a baseline for future algorithm comparison, we evaluate a public research release of genetic programming symbolic regression algorithm on a sampling of the framework's benchmarks.Back to 2011 Publications
About the Group
Private or Protected Links