Award Date

12-2011

Degree Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science

First Committee Member

Matt Pedersen, Chair

Second Committee Member

Kazem Taghva

Third Committee Member

John Minor

Graduate Faculty Representative

Aly Said

Number of Pages

84

Abstract

An artificial neural network can be used to solve various statistical problems by approximating a function that provides a mapping from input to output data. No universal method exists for architecting an optimal neural network. Training one with a low error rate is often a manual process requiring the programmer to have specialized knowledge of the domain for the problem at hand.

A distributed architecture is proposed and implemented for generating a neural network capable of solving a particular problem without specialized knowledge of the problem domain. The only knowledge the application needs is a training set that the network will be trained with. The application uses a master-slave architecture to generate and select a neural network capable of solving a given problem.

Keywords

Applied sciences; Clojure (Computer program language); JMS; Mathematical optimization; Network; Neural; Neural networks (Computer science); Optimize; Stochastic processes

Disciplines

Artificial Intelligence and Robotics | Computer Sciences | Statistical Methodology

Language

English


Share

COinS