BASS : Broad Network Based on Localized Stochastic Sensitivity
The training of the standard broad learning system (BLS) concerns the optimization of its output weights via the minimization of both training mean square error (MSE) and a penalty term. However, it degrades the generalization capability and robustness of BLS when facing complex and noisy environments, especially when small perturbations or noise appear in input data. Therefore, this work proposes a broad network based on localized stochastic sensitivity (BASS) algorithm to tackle the issue of noise or input perturbations from a local perturbation perspective. The localized stochastic sensitivity (LSS) prompts an increase in the network's noise robustness by considering unseen samples located within a Q -neighborhood of training samples, which enhances the generalization capability of BASS with respect to noisy and perturbed data. Then, three incremental learning algorithms are derived to update BASS quickly when new samples arrive or the network is deemed to be expanded, without retraining the entire model. Due to the inherent superiorities of the LSS, extensive experimental results on 13 benchmark datasets show that BASS yields better accuracies on various regression and classification problems. For instance, BASS uses fewer parameters (12.6 million) to yield 1% higher Top-1 accuracy in comparison to AlexNet (60 million) on the large-scale ImageNet (ILSVRC2012) dataset.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:35 |
|---|---|
| Enthalten in: |
IEEE transactions on neural networks and learning systems - 35(2024), 2 vom: 13. Feb., Seite 1681-1695 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wang, Ting [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 17.02.2024 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1109/TNNLS.2022.3184846 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM343507463 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM343507463 | ||
| 003 | DE-627 | ||
| 005 | 20240217231943.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TNNLS.2022.3184846 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1297.xml |
| 035 | |a (DE-627)NLM343507463 | ||
| 035 | |a (NLM)35830397 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wang, Ting |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a BASS |b Broad Network Based on Localized Stochastic Sensitivity |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 17.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a The training of the standard broad learning system (BLS) concerns the optimization of its output weights via the minimization of both training mean square error (MSE) and a penalty term. However, it degrades the generalization capability and robustness of BLS when facing complex and noisy environments, especially when small perturbations or noise appear in input data. Therefore, this work proposes a broad network based on localized stochastic sensitivity (BASS) algorithm to tackle the issue of noise or input perturbations from a local perturbation perspective. The localized stochastic sensitivity (LSS) prompts an increase in the network's noise robustness by considering unseen samples located within a Q -neighborhood of training samples, which enhances the generalization capability of BASS with respect to noisy and perturbed data. Then, three incremental learning algorithms are derived to update BASS quickly when new samples arrive or the network is deemed to be expanded, without retraining the entire model. Due to the inherent superiorities of the LSS, extensive experimental results on 13 benchmark datasets show that BASS yields better accuracies on various regression and classification problems. For instance, BASS uses fewer parameters (12.6 million) to yield 1% higher Top-1 accuracy in comparison to AlexNet (60 million) on the large-scale ImageNet (ILSVRC2012) dataset | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Zhang, Mingyang |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Jianjun |e verfasserin |4 aut | |
| 700 | 1 | |a Ng, Wing W Y |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, C L Philip |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on neural networks and learning systems |d 2012 |g 35(2024), 2 vom: 13. Feb., Seite 1681-1695 |w (DE-627)NLM23236897X |x 2162-2388 |7 nnns |
| 773 | 1 | 8 | |g volume:35 |g year:2024 |g number:2 |g day:13 |g month:02 |g pages:1681-1695 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TNNLS.2022.3184846 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 35 |j 2024 |e 2 |b 13 |c 02 |h 1681-1695 | ||