Characteristics of different deep neural networks and application of pre-trained model without transfer learning

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.

Name thesis:degree_name

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

Discipline thesis:degree_discipline

Computer Science

Year

2017

Author dc:creator

• Peng, Zhiqi

Contributors dc:contributor

• Zhi Wei
• Usman W. Roshan
• Hai Nhat Phan

• Deep neural networks
• Data simulations
• Computer Sciences

Repository record dc:identifier

https://digitalcommons.njit.edu/theses/40

OAI identifier oai:identifier

oai:digitalcommons.njit.edu:theses-1039