UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
General-Purpose Optimization Through Information-Maximization (2012)
Alan J Lockett
The primary goal of artificial intelligence research is to develop a machine capable of learning to solve disparate real-world tasks autonomously, without relying on specialized problem-specific inputs. This dissertation suggests that such machines are realistic: If No Free Lunch theorems were to apply to all real-world problems, then the world would be utterly unpredictable. In response, the dissertation proposes the information-maximization principle, which claims that the optimal optimization methods make the best use of the information available to them. This principle results in a new algorithm, evolutionary annealing, which is shown to perform well especially in challenging problems with irregular structure.
View:
PDF
Citation:
PhD Thesis, Department of Computer Sciences, The University of Texas at Austin. Tech Report AI12-11.
Bibtex:
@phdthesis{lockett:phd12, title={General-Purpose Optimization Through Information-Maximization}, author={Alan J Lockett}, school={Department of Computer Sciences, The University of Texas at Austin}, institution={Department of Computer Sciences, The University of Texas at Austin}, note={Tech Report AI12-11}, url="http://www.cs.utexas.edu/users/ai-lab?lockett:phd12", year={2012} }
People
Alan J. Lockett
Ph.D. Alumni
alan lockett [at] gmail com
Projects
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Areas of Interest
Control
Evolutionary Computation
Neuroevolution
Theory of Evolutionary Computation
Software/Data
PyEC
Python package containing source code for Evolutionary Annealing along with a number of other evolutionary and stochasti...
2011
Labs
Neural Networks