Speaker: Janusz Wojtusiak, Department of Health Administration and Policy, George Mason University
Title: Selected Aspects of the Learnable Evolution Model
The Learnable Evolution Model (LEM) is an evolutionary optimization method that uses machine learning to guide the evolution process. At each stage of evolution LEM selects high- and low-performing candidate solutions, and hypothesizes about their properties. These hypotheses are instantiated to create new candidate solutions. Experimental results from different implementations of LEM indicated its very good performance when compared to traditional evolutionary computation methods. This talk gives an introduction to LEM and presents its selected aspects available in its implementation called LEM3. These include: improving representation spaces, and solving multitype optimization problems.
Time: Friday, Feb. 6, 2009, 1:30-2:30 p.m.
Place: Science and Tech I, Room 242
Department of Mathematical Sciences
George Mason University
4400 University Drive, MS 3F2
Fairfax, VA 22030-4444
Tel. 703-993-1460, Fax. 703-993-1491