Feature selection for classification applications in neural network pruning
The feature selection problem, which is a traditional machine learning problem, share many similarities with neural network pruning problem. However, traditional feature selection techniques are less visited in neural network pruning. To bridge this gap, comprehensive literature reviews on both f...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/172919 |
| _version_ | 1824453630778933248 |
|---|---|
| author | Gong, Rui |
| author2 | Mao Kezhi |
| author_facet | Mao Kezhi Gong, Rui |
| author_sort | Gong, Rui |
| collection | NTU |
| description | The feature selection problem, which is a traditional machine learning problem,
share many similarities with neural network pruning problem. However, traditional
feature selection techniques are less visited in neural network pruning. To
bridge this gap, comprehensive literature reviews on both fields are conducted
in this dissertation. Then the neural network pruning problem is formulated as
a feature selection problems, and feature selection methods are introduced to
prune neural networks. Experiments results show that feature selection methods
are useful for neural network pruning. |
| first_indexed | 2025-02-19T03:09:29Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/172919 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:09:29Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1729192024-01-12T15:45:59Z Feature selection for classification applications in neural network pruning Gong, Rui Mao Kezhi School of Electrical and Electronic Engineering EKZMao@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence The feature selection problem, which is a traditional machine learning problem, share many similarities with neural network pruning problem. However, traditional feature selection techniques are less visited in neural network pruning. To bridge this gap, comprehensive literature reviews on both fields are conducted in this dissertation. Then the neural network pruning problem is formulated as a feature selection problems, and feature selection methods are introduced to prune neural networks. Experiments results show that feature selection methods are useful for neural network pruning. Master of Science (Computer Control and Automation) 2024-01-07T12:11:13Z 2024-01-07T12:11:13Z 2023 Thesis-Master by Coursework Gong, R. (2023). Feature selection for classification applications in neural network pruning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/172919 https://hdl.handle.net/10356/172919 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Gong, Rui Feature selection for classification applications in neural network pruning |
| title | Feature selection for classification applications in neural network pruning |
| title_full | Feature selection for classification applications in neural network pruning |
| title_fullStr | Feature selection for classification applications in neural network pruning |
| title_full_unstemmed | Feature selection for classification applications in neural network pruning |
| title_short | Feature selection for classification applications in neural network pruning |
| title_sort | feature selection for classification applications in neural network pruning |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/172919 |
| work_keys_str_mv | AT gongrui featureselectionforclassificationapplicationsinneuralnetworkpruning |