Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method?
To overcome the pitfalls of Random Vector Functional Link (RVFL), a network called Stochastic Configuration Networks (SCN) has been proposed. By constraining and adaptively selecting the range of randomized parameters using the Stochastic Configuration (SC) algorithm, SCN claims to be potent in buil...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/162758 |
| _version_ | 1826116419300884480 |
|---|---|
| author | Hu, Minghui Suganthan, Ponnuthurai Nagaratnam |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Hu, Minghui Suganthan, Ponnuthurai Nagaratnam |
| author_sort | Hu, Minghui |
| collection | NTU |
| description | To overcome the pitfalls of Random Vector Functional Link (RVFL), a network called Stochastic Configuration Networks (SCN) has been proposed. By constraining and adaptively selecting the range of randomized parameters using the Stochastic Configuration (SC) algorithm, SCN claims to be potent in building an incremental randomized learning system according to residual error minimization. The SC has three variants depending on how the range of output weights are updated. In this work, we first relate the SCN to appropriate literature. Subsequently, we show that the major parts of the SC algorithm can be replaced by a generic hyper-parameter optimization method to obtain overall better results. |
| first_indexed | 2024-10-01T04:11:05Z |
| format | Journal Article |
| id | ntu-10356/162758 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:11:05Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1627582022-11-09T02:16:39Z Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? Hu, Minghui Suganthan, Ponnuthurai Nagaratnam School of Electrical and Electronic Engineering Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Randomized Neural Network Stochastic Configuration Network To overcome the pitfalls of Random Vector Functional Link (RVFL), a network called Stochastic Configuration Networks (SCN) has been proposed. By constraining and adaptively selecting the range of randomized parameters using the Stochastic Configuration (SC) algorithm, SCN claims to be potent in building an incremental randomized learning system according to residual error minimization. The SC has three variants depending on how the range of output weights are updated. In this work, we first relate the SCN to appropriate literature. Subsequently, we show that the major parts of the SC algorithm can be replaced by a generic hyper-parameter optimization method to obtain overall better results. Submitted/Accepted version 2022-11-09T02:16:39Z 2022-11-09T02:16:39Z 2022 Journal Article Hu, M. & Suganthan, P. N. (2022). Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method?. Applied Soft Computing, 126, 109257-. https://dx.doi.org/10.1016/j.asoc.2022.109257 1568-4946 https://hdl.handle.net/10356/162758 10.1016/j.asoc.2022.109257 2-s2.0-85134435218 126 109257 en Applied Soft Computing © 2022 Elsevier B.V. All rights reserved. This paper was published in Applied Soft Computing and is made available with permission of Elsevier B.V. application/pdf |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Randomized Neural Network Stochastic Configuration Network Hu, Minghui Suganthan, Ponnuthurai Nagaratnam Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? |
| title | Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? |
| title_full | Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? |
| title_fullStr | Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? |
| title_full_unstemmed | Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? |
| title_short | Experimental evaluation of stochastic configuration networks: is SC algorithm inferior to hyper-parameter optimization method? |
| title_sort | experimental evaluation of stochastic configuration networks is sc algorithm inferior to hyper parameter optimization method |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Randomized Neural Network Stochastic Configuration Network |
| url | https://hdl.handle.net/10356/162758 |
| work_keys_str_mv | AT huminghui experimentalevaluationofstochasticconfigurationnetworksisscalgorithminferiortohyperparameteroptimizationmethod AT suganthanponnuthurainagaratnam experimentalevaluationofstochasticconfigurationnetworksisscalgorithminferiortohyperparameteroptimizationmethod |