UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Brian Greer
, Henri Hakonen, Risto Lahdelma, and
Risto Miikkulainen
Neuroevolution techniques have been successful in many sequential decision tasks such as robot control and game playing. This paper aims at establishing whether they can be useful in numerical optimization more generally, by comparing neuroevolution to linear programming in a manufacturing optimization domain. It turns out that neuroevolution can learn to compensate for uncertainty in the data and outperform linear programming when the number of variables in the problem is small and the required precision is low, but the current techniques do not (yet) provide an advantage in problems where many variables must be optimized with high precision.
View:
PDF
,
PS
Citation:
In
Proceedings of the 2002 Congress on Evolutionary Computation
, pp. 361-401, Piscataway, NJ 2002. IEEE. Undergraduate Thesis, Department of Computer Sciences, The University of Texas at Austin.
Bibtex:
@Misc{greer:ugthesis01, title={Numerical Optimization With Neuroevolution}, author={Brian Greer and Henri Hakonen and Risto Lahdelma and Risto Miikkulainen}, booktitle={Proceedings of the 2002 Congress on Evolutionary Computation}, address={Piscataway, NJ}, publisher={IEEE}, pages={361-401}, note={Undergraduate Thesis, Department of Computer Sciences, The University of Texas at Austin}, url="http://www.cs.utexas.edu/users/ai-lab/?greer:cec02", year={2002} }
People
Brian Greer
Undergraduate Alumni
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Projects
Optimizing a Manufacturing Process
1998 - 2002
Areas of Interest
Applications
Evolutionary Computation
Neuroevolution
Reinforcement Learning
Labs
Neural Networks