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.
Recommended Citation
Peng, Zhiqi, "Characteristics of different deep neural networks and application of pre-trained model without transfer learning" (2017). Theses. 40.
https://digitalcommons.njit.edu/theses/40
