Development of a learning system for convolutional neural network
Traditional learning system of convolutional neural network (CNN) is based on gradient descent method and back propagation. Effective though it is, we still keep seeking new learning system to make possible progress. For this purpose, we try to utilize incremental learning algorithm which is shown e...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/143339 |
| _version_ | 1826129931901337600 |
|---|---|
| author | Liu, Hang |
| author2 | CHEAH Chien Chern |
| author_facet | CHEAH Chien Chern Liu, Hang |
| author_sort | Liu, Hang |
| collection | NTU |
| description | Traditional learning system of convolutional neural network (CNN) is based on gradient descent method and back propagation. Effective though it is, we still keep seeking new learning system to make possible progress. For this purpose, we try to utilize incremental learning algorithm which is shown effective on the approximation of robot kinematic model and forward thinking framework as alternatives. This dissertation is mainly about the preliminary work we do before combining these two algorithms together. We investigate the performance of incremental learning algorithm for a single hidden layer feed forward network and the fully connected part of CNN, with comparison to traditional learning algorithm. We also verify the effectiveness of the forward thinking framework in CNN. Furthermore, the effect of the number of layers of shallow network in forward thinking framework is investigated. |
| first_indexed | 2024-10-01T07:48:17Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/143339 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:48:17Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1433392023-07-04T15:41:16Z Development of a learning system for convolutional neural network Liu, Hang CHEAH Chien Chern School of Electrical and Electronic Engineering ECCCheah@ntu.edu.sg Engineering::Electrical and electronic engineering::Control and instrumentation Traditional learning system of convolutional neural network (CNN) is based on gradient descent method and back propagation. Effective though it is, we still keep seeking new learning system to make possible progress. For this purpose, we try to utilize incremental learning algorithm which is shown effective on the approximation of robot kinematic model and forward thinking framework as alternatives. This dissertation is mainly about the preliminary work we do before combining these two algorithms together. We investigate the performance of incremental learning algorithm for a single hidden layer feed forward network and the fully connected part of CNN, with comparison to traditional learning algorithm. We also verify the effectiveness of the forward thinking framework in CNN. Furthermore, the effect of the number of layers of shallow network in forward thinking framework is investigated. Master of Science (Computer Control and Automation) 2020-08-25T06:16:33Z 2020-08-25T06:16:33Z 2020 Thesis-Master by Coursework https://hdl.handle.net/10356/143339 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering::Control and instrumentation Liu, Hang Development of a learning system for convolutional neural network |
| title | Development of a learning system for convolutional neural network |
| title_full | Development of a learning system for convolutional neural network |
| title_fullStr | Development of a learning system for convolutional neural network |
| title_full_unstemmed | Development of a learning system for convolutional neural network |
| title_short | Development of a learning system for convolutional neural network |
| title_sort | development of a learning system for convolutional neural network |
| topic | Engineering::Electrical and electronic engineering::Control and instrumentation |
| url | https://hdl.handle.net/10356/143339 |
| work_keys_str_mv | AT liuhang developmentofalearningsystemforconvolutionalneuralnetwork |