Advisor(s)
Marsette Vona
Contributor(s)
Joseph Ayers
Date of Award
2012
Date Accepted
4-2012
Degree Grantor
Northeastern University
Degree Level
M.S.
Degree Name
Master of Science
Department or Academic Unit
College of Computer and Information Science. Department of Computer Science.
Keywords
computer science, artificial intelligence, artificial life, functional blueprints, neuroevolution
Subject Categories
Machine learning, Artificial intelligence
Disciplines
Artificial Intelligence and Robotics
Abstract
Neuroevolution algorithms are an important tool for optimizing neural network design in the fields of control and machine learning. We seek to improve SANE, a classic machine learning algorithm, by optimizing the size of the hidden layer in the neural networks that it generates. We use a technique called functional blueprints that guide the self-organization of systems by specifying their desired behavior, in this case avoidance of over/underfitting. We performed experiments with a simulated double cart-pole balancing benchmark problem which indicate that BlueSANE improves performance by slight to moderate amounts compared to the original SANE algorithm.
Document Type
Master's Thesis
Rights Holder
Jessica H. Lowell
Permanent URL
Recommended Citation
Lowell, Jessica H., "BlueSANE: integrating functional blueprints with neuroevolution" (2012). Computer Science Master's Theses. Paper 6. http://hdl.handle.net/2047/d20002569
Click button above to open, or right-click to save.