Document Type

Thesis

Date of Award

Fall 12-31-2017

Degree Name

Master of Science in Computer Science - (M.S.)

Department

Computer Science

First Advisor

Zhi Wei

Second Advisor

Usman W. Roshan

Third Advisor

Hai Nhat Phan

Abstract

Deep neural networks have been successful in many areas, some of them even surpass human performances. The goal of this thesis is using data simulations to present different characteristics of three deep neural networks: fully connected deep neural network, convolutional neural network, recurrent neural network, which will perform best when dealing with different feature patterns. By using these characteristics to design a deep neural network on top of an adopted pre-trained model with untrainable layers, achieved an averagely 11.1% improvement than a model with transfer learning method.

Share

COinS