Multi-Task Learning Based on Stochastic Configuration Networks
When the human brain learns multiple related or continuous tasks, it will produce knowledge sharing and transfer. Thus, fast and effective task learning can be realized. This idea leads to multi-task learning. The key of multi-task learning is to find the correlation between tasks and establish a fa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-08-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2022.890132/full |
| _version_ | 1827854450771886080 |
|---|---|
| author | Xue-Mei Dong Xudong Kong Xiaoping Zhang |
| author_facet | Xue-Mei Dong Xudong Kong Xiaoping Zhang |
| author_sort | Xue-Mei Dong |
| collection | DOAJ |
| description | When the human brain learns multiple related or continuous tasks, it will produce knowledge sharing and transfer. Thus, fast and effective task learning can be realized. This idea leads to multi-task learning. The key of multi-task learning is to find the correlation between tasks and establish a fast and effective model based on these relationship information. This paper proposes a multi-task learning framework based on stochastic configuration networks. It organically combines the idea of the classical parameter sharing multi-task learning with that of constraint sharing configuration in stochastic configuration networks. Moreover, it provides an efficient multi-kernel function selection mechanism. The convergence of the proposed algorithm is proved theoretically. The experiment results on one simulation data set and four real life data sets verify the effectiveness of the proposed algorithm. |
| first_indexed | 2024-03-12T11:22:55Z |
| format | Article |
| id | doaj.art-5da017f7773a4d188a6cd139945313c2 |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-03-12T11:22:55Z |
| publishDate | 2022-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-5da017f7773a4d188a6cd139945313c22023-09-01T14:16:36ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852022-08-011010.3389/fbioe.2022.890132890132Multi-Task Learning Based on Stochastic Configuration NetworksXue-Mei DongXudong KongXiaoping ZhangWhen the human brain learns multiple related or continuous tasks, it will produce knowledge sharing and transfer. Thus, fast and effective task learning can be realized. This idea leads to multi-task learning. The key of multi-task learning is to find the correlation between tasks and establish a fast and effective model based on these relationship information. This paper proposes a multi-task learning framework based on stochastic configuration networks. It organically combines the idea of the classical parameter sharing multi-task learning with that of constraint sharing configuration in stochastic configuration networks. Moreover, it provides an efficient multi-kernel function selection mechanism. The convergence of the proposed algorithm is proved theoretically. The experiment results on one simulation data set and four real life data sets verify the effectiveness of the proposed algorithm.https://www.frontiersin.org/articles/10.3389/fbioe.2022.890132/fullmulti-task learningneural networksstochastic configurationknowledge sharing and transfersupervised mechanism |
| spellingShingle | Xue-Mei Dong Xudong Kong Xiaoping Zhang Multi-Task Learning Based on Stochastic Configuration Networks Frontiers in Bioengineering and Biotechnology multi-task learning neural networks stochastic configuration knowledge sharing and transfer supervised mechanism |
| title | Multi-Task Learning Based on Stochastic Configuration Networks |
| title_full | Multi-Task Learning Based on Stochastic Configuration Networks |
| title_fullStr | Multi-Task Learning Based on Stochastic Configuration Networks |
| title_full_unstemmed | Multi-Task Learning Based on Stochastic Configuration Networks |
| title_short | Multi-Task Learning Based on Stochastic Configuration Networks |
| title_sort | multi task learning based on stochastic configuration networks |
| topic | multi-task learning neural networks stochastic configuration knowledge sharing and transfer supervised mechanism |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2022.890132/full |
| work_keys_str_mv | AT xuemeidong multitasklearningbasedonstochasticconfigurationnetworks AT xudongkong multitasklearningbasedonstochasticconfigurationnetworks AT xiaopingzhang multitasklearningbasedonstochasticconfigurationnetworks |