Extreme learning machine with sparse connections
The thesis is in the field of machine learning, and specifically studies the recent emerging algorithm, Extreme Learning Machine (ELM). Unlike previous ELM implementations, in which hidden nodes are in full connection with the input ones, we present the ELM with sparse connections. In one way, it re...
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Thesis |
| 語言: | English |
| 出版: |
2015
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/65656 |
| _version_ | 1826114058701504512 |
|---|---|
| author | Bai, Zuo |
| author2 | Wang Dan Wei |
| author_facet | Wang Dan Wei Bai, Zuo |
| author_sort | Bai, Zuo |
| collection | NTU |
| description | The thesis is in the field of machine learning, and specifically studies the recent emerging algorithm, Extreme Learning Machine (ELM). Unlike previous ELM implementations, in which hidden nodes are in full connection with the input ones, we present the ELM with sparse connections. In one way, it reduces the storage space and testing time, while providing better scalability for large-scale applications. In the other way, the sparse connections make it especially suitable and efficient for locally correlated applications, such as image processing, speech recognition, etc. |
| first_indexed | 2024-10-01T03:32:58Z |
| format | Thesis |
| id | ntu-10356/65656 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:32:58Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | ntu-10356/656562023-07-04T16:27:03Z Extreme learning machine with sparse connections Bai, Zuo Wang Dan Wei Huang Guangbin School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence The thesis is in the field of machine learning, and specifically studies the recent emerging algorithm, Extreme Learning Machine (ELM). Unlike previous ELM implementations, in which hidden nodes are in full connection with the input ones, we present the ELM with sparse connections. In one way, it reduces the storage space and testing time, while providing better scalability for large-scale applications. In the other way, the sparse connections make it especially suitable and efficient for locally correlated applications, such as image processing, speech recognition, etc. DOCTOR OF PHILOSOPHY (EEE) 2015-12-01T08:22:50Z 2015-12-01T08:22:50Z 2015 2015 Thesis Bai, Z. (2015). Extreme learning machine with sparse connections. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/65656 10.32657/10356/65656 en 143 p application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Bai, Zuo Extreme learning machine with sparse connections |
| title | Extreme learning machine with sparse connections |
| title_full | Extreme learning machine with sparse connections |
| title_fullStr | Extreme learning machine with sparse connections |
| title_full_unstemmed | Extreme learning machine with sparse connections |
| title_short | Extreme learning machine with sparse connections |
| title_sort | extreme learning machine with sparse connections |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/65656 |
| work_keys_str_mv | AT baizuo extremelearningmachinewithsparseconnections |