Date of Award

2009

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

School of Computer Science and Engineering

First Advisor

Georgiou, George M.

Second Advisor

Voigt, Kerstin

Third Advisor

Gomez, Ernesto

Abstract

The purpose of this thesis will be to demostrate the feasibility of building a system that is capable of automatically learning how to increase performance at a task that is presented to it by means of modeling the problem with a finite automation and the learning engine of FABLE. Current work in the field of automatic learning of FA's (Finite Automation) is mostly focused on the building of the FA itself. This thesis will instead focus on the automated building of FA models to allow better decisions to be made in the future.

Share

COinS