Date of Award

12-1996

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Electrical and Computer Engineering

First Advisor

Steven K. Rogers, PhD

Abstract

This research develops a general methodology for designing neural network classifiers for real-world environmental problems. This methodology is demonstrated through the design of a multi-layer perceptron to classify stainless steel and actinide samples. Neural networks, sometimes called artificial neural networks, have been shown capable of classifying complex patterns. Artificial neural networks are physiologically motivated computer algorithms which attempt to mimic the function of the large interconnected network of neurons in the human brain, which has extraordinary pattern recognition capabilities. These artificial neural networks learn to map a set of input features, elemental composition, onto a set of outputs such as a binary node whose output (1 or 0) represents steel or not steel. For this reason, neural networks may be used to classify the given environmental data.

AFIT Designator

AFIT-GEE-ENG-96D-04

DTIC Accession Number

ADA321663

Share

COinS