Abstract
Broad neural networks provide an alternative way of deep learning with a novel flatted structure, which employ a non-iterative training mechanism and exhibit high efficiency in various recognition tasks. However, such broad networks unavoidably suffer from unstable performance due to the double random mappings in the generation of feature representations and the consequent uncertainty. The existing research often neglect to explore the effect of the quality of the broaden feature representations, which is crucial for the model performance. This paper presents a progressively-enhanced framework taking broad network as basic learners (PE-BL) to address the existing issues. The basic broad learners in PE-BL are trained in sequence, and the core manipulation is to modify the primitive hidden feature representations of the current learner through the nonlinear transformation of the prediction from the previous one, so the resulting broaden representations become more discriminative. Further, PE-BL is adapted to the scenarios where only a single broad learner is employed. Finally, extensive comparative experiments on some benchmark datasets and Electroencephalogram (EEG)-based emotion recognition task verify the effectiveness of the proposed methods.
Similar content being viewed by others
References
Chen CLP, Liu Z (2018) Broad learning system: an effective and efficient incremental learning system without the need for deep architecture. IEEE Trans Neural Netw Learn Syst 29(1):10–24. https://doi.org/10.1109/TNNLS.2017.2716952
Chen CLP, Liu Z, Shuang F (2019) Universal approximation capability of broad learning system and its structural variations. IEEE Trans Neural Netw Learn Syst 30 (4):1191–1204. https://doi.org/10.1109/TNNLS.2018.2866622
Chu Y, Lin H, Yang L, Sun S, Diao Y, Min C, Fan X, Shen C (2021) Hyperspectral image classification with discriminative manifold broad learning system. Neurocomputing 442:236–248. https://doi.org/10.1016/j.neucom.2021.01.120
Ding W, Tian Y, Han S, Yuan H (2021) Greedy broad learning system. IEEE Access 9:79,307–79,315. https://doi.org/10.1109/ACCESS.2021.3084610
Duan R, Zhu J, Lu B (2013) .. In: 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER), pp 81–84
Gao Q, Wang C, Wang Z, Song X, Dong E, Song Y (2020) EEG Based emotion recognition using fusion feature extraction method. Multimed Tools Appl 79 (37-38):27,057–27,074. https://doi.org/10.1007/s11042-020-09354-y
Gao Z, Wang X, Yang Y, Li Y, Ma K, Chen G (2021) A channel-fused dense convolutional network for EEG-based emotion recognition. IEEE Trans Cogn Develop Syst 13(4):945–954. https://doi.org/10.1109/TCDS.2020.2976112
Guo P (2020) On the structure evolutionary of the pseudoinverse learners in synergetic learning systems. Preprint researchgate.net. https://doi.org/10.13140/RG.2.2.12262.45121
Guo P, Chen CLP, Sun Y (1996) AHLN Algorithm: perfect learning through data representation. Journal of Beijing Normal University (Natural Science Edition) 32(1):71–75
Guo P, Yin Q (2020) Synergetic learning systems: concept, architecture, and algorithms. Preprint, arXiv, 01 2020
Han M, Feng S, Chen CLP, Xu M, Qiu T (2019) Structured manifold broad learning system: a manifold perspective for large-scale chaotic time series analysis and prediction. IEEE Trans Knowl Data Eng 31(9):1809–1821. https://doi.org/10.1109/TKDE.2018.2866149
He K, Zhang X, Ren S, Sun J (2016) .. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016. https://doi.org/10.1109/CVPR.2016.90, pp 770–778
Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554. https://doi.org/10.1162/neco.2006.18.7.1527
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507. https://doi.org/10.1162/neco.2006.18.7.1527
Jin J, Li Y, Yang T, Zhao L, Duan J, Chen CLP (2021) Discriminative group-sparsity constrained broad learning system for visual recognition. Inf Sci 576:800–818. https://doi.org/10.1016/j.ins.2021.06.008
Jin J, Liu Z, Chen CLP (2018) Discriminative graph regularized broad learning system for image recognition. Science China(Information Sciences) 112,209:1–112,209(11):14. https://doi.org/10.1007/s11432-017-9421-3
Keshmiri S, Sumioka H, Nakanishi J, Ishiguro H (2017) .. In: 2017 international joint conference on neural networks, IJCNN 2017, Anchorage, AK, USA, May 14-19, 2017. https://doi.org/10.1109/IJCNN.2017.7966409, pp 4371–4378
Kohonen T (2001) Self-Organizing Maps springer series in information sciences. Springer. https://doi.org/10.1007/978-3-642-56927-2
Kong Y, Wang X, Cheng Y, Chen CLP (2018) Hyperspectral imagery classification based on semi-supervised broad learning system. Remote Sens 10(5):685. https://doi.org/10.3390/rs10050685
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Li J, Zhang Z, He H (2018) Hierarchical convolutional neural networks for EEG-based emotion recognition. Cognit Comput 10(2):368–380. https://doi.org/10.1007/s12559-017-9533-x
Li Y, Zheng W, Cui Z, Zhou X (2016) .. In: Neural information processing - 23rd international conference, ICONIP 2016, Kyoto, Japan, October 16-21, 2016, Proceedings, Part IV, vol 9950. https://doi.org/10.1007/978-3-319-46681-1_21, pp 175–182
Liang C, Lao H, Wei T, Zhang X (2022) Alzheimer’s disease classification from hippocampal atrophy based on pcanet-bls. Multimed Tools Appl 81(8):11,187–11,203. https://doi.org/10.1007/s11042-022-12228-0
Liu Z, Chen CLP, Feng S, Feng Q, Zhang T (2021) Stacked broad learning system: from incremental flatted structure to deep model. IEEE Trans Syst Man Cybern Syst 51(1):209–222. https://doi.org/10.1109/TSMC.2020.3043147
Liu Z, Huang S, Jin W, Mu Y (2021) Broad learning system for semi-supervised learning. Neurocomputing 444:38–47. https://doi.org/10.1016/j.neucom.2021.02.059
Liu W, Zheng W, Lu B (2016) .. In: Neural information processing - 23rd international conference, ICONIP 2016, Kyoto, Japan, October 16-21, 2016, Proceedings, Part II, vol 9948. https://doi.org/10.1007/978-3-319-46672-9_58, pp 521–529
Nakisa B, Rastgoo MN, Tjondronegoro D, Chandran V (2018) Evolutionary computation algorithms for feature selection of eeg-based emotion recognition using mobile sensors. Expert Syst Appl 93:143–155. https://doi.org/10.1016/j.eswa.2017.09.062
Pao Y, Park GH, Sobajic DJ (1994) Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6(2):163–180. https://doi.org/10.1016/0925-2312(94)90053-1
Rifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) .. In: Proceedings of the 28th international conference on machine learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011. https://icml.cc/2011/papers/455_icmlpaper.pdf, pp 833–840
Schäfer D, Hüllermeier E (2018) Dyad ranking using plackett-luce models based on joint feature representations. Mach Learn 107(5):903–941. https://doi.org/10.1007/s10994-017-5694-9
Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol P (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J Mach Learn Res 11:3371–3408
Wang K, Guo P (2021) An ensemble classification model with unsupervised representation learning for driving stress recognition using physiological signals. IEEE Trans Intell Transp Syst 22(6):3303–3315. https://doi.org/10.1109/TITS.2020.2980555
Wang K, Guo P, Luo A (2017) A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery. Monthly Notices of the Royal Astronomical Society (4) 4311–4324
Xie R, Wang S (2020) Downsizing and enhancing broad learning systems by feature augmentation and residuals boosting. Complex Intell Syst 6(2):411–429
Xu B, Guo P (2018) .. In: IEEE international conference on systems, man, and cybernetics, SMC 2018, Miyazaki, Japan, October 7-10, 2018, pp 4243–4247
Ye H, Li H, Chen CLP (2021) Adaptive deep cascade broad learning system and its application in image denoising. IEEE Trans Cybern 51(9):4450–4463. https://doi.org/10.1109/TCYB.2020.2978500
Yin Q, Xu B, Zhou K, Guo P (2021) Bayesian pseudoinverse learners: from uncertainty to deterministic learning. IEEE Trans Cybern PP(99):1–12
Zhang L, Li J, Lu G, Shen P, Bennamoun M, Shah SAA, Miao Q, Zhu G, Li P, Lu X (2022) Analysis and variants of broad learning system. IEEE Trans Syst Man Cybern Syst 52(1):334–344. https://doi.org/10.1109/TSMC.2020.2995205
Zhang L, Suganthan PN (2016) A comprehensive evaluation of random vector functional link networks. Inf Sci 367-368:1094–1105. https://doi.org/10.1016/j.ins.2015.09.025
Zhang T, Zheng W, Cui Z, Zong Y, Li Y (2019) Spatial-temporal recurrent neural network for emotion recognition. IEEE Trans Cybern 49 (3):839–847. https://doi.org/10.1109/TCYB.2017.2788081
Zhang D, Zhou Z, Chen S (2006) Diagonal principal component analysis for face recognition. Pattern Recogn 39(1):140–142. https://doi.org/10.1016/j.patcog.2005.08.002
Zhao H, Zheng J, Deng W, Song Y (2020) Semi-supervised broad learning system based on manifold regularization and broad network. IEEE Trans Circuits Syst I: Regul Pap 67-I(3):983–994. https://doi.org/10.1109/TCSI.2019.2959886
Zheng W (2017) Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis. IEEE Trans Cogn Develop Syst 9(3):281–290. https://doi.org/10.1109/TCDS.2016.2587290
Zheng W, Lu B (2015) Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks. IEEE Trans Auton Ment Dev 7(3):162–175. https://doi.org/10.1109/TAMD.2015.2431497
Acknowledgements
This work is supported in part by the National Key Research and Development Program of China under Grant 2018AAA0100203, and in part by the Joint Research Fund in Astronomy (U2031136) under cooperative agreement between the NSFC and CAS.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Data availability
Data sharing is not applicable to this article as no new datasets were generated or analyzed during the current study.
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sun, X., Chen, B., Shi, R. et al. A progressively-enhanced framework to broad networks for efficient recognition applications. Multimed Tools Appl 82, 24865–24890 (2023). https://doi.org/10.1007/s11042-022-14087-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14087-1