Abstract
Broad learning system (BLS) is an emerging machine learning algorithm with high efficiency and good approximation capability. It has been proved that BLS can learn hundreds of times faster than traditional deep learning algorithms while providing a comparable or even better generalization performance. Owing to its superb efficiency and powerful learning ability, the BLS is attracting increasing attention from machine learning community and can be considered as an alternative to deep learning in some situations. However, due to its shallow structure, the feature learning of BLS is not sufficient and which may probably limit its learning performance. For this issue, this paper proposes a novel hierarchical broad learning system (H-BLS) with deep and sparse feature learning. Different from the original BLS which conducts feature learning simply using a single-layer function mapping, the H-BLS adopts a hierarchical feature learning framework with multi-layer and multi-group structure to extract high-level and rich feature information from the original input, so as to improve the feature representation capability of the model. Meanwhile, in the hierarchical feature learning process of H-BLS, a new l1-constrained sparse autoencoder is employed and embedded in each layer of the framework for feature reconstruction, so as to eliminate redundancy of the input and generate more sparse and compact feature representations, thus further enhancing its learning performance. The learning ability of the proposed H-BLS is firstly evaluated by ten commonly used regression data sets, and the experimental results show that H-BLS performs better compared with several representative learning algorithms such as SVM, LSSVM, ELM, BLS and two recently proposed BLS variants. Moreover, the H-BLS also shows advantages over the state-of-the-art methods in terms of classification accuracy and training time on image classification problems.
Similar content being viewed by others
Change history
28 October 2023
A Correction to this paper has been published: https://doi.org/10.1007/s10489-023-05100-7
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 Networks Learn Syst 29(1):10–24. https://doi.org/10.1109/TNNLS.2017.2716952
Igelnik B, Pao YH (1995) Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Trans Neural Netw 6(6):1320–1329. https://doi.org/10.1109/72.471375
Chen CLP, Liu ZL, Feng S (2019) Universal approximation capability of broad learning system and its structural variations. IEEE Trans Neural Networks Learn Syst 30(4):1191–1204. https://doi.org/10.1109/tnnls.2018.2866622
Feng S, Chen CLP (2020) Fuzzy broad learning system: a novel neuro-fuzzy model for regression and classification. IEEE Trans Cybern 50(2):414–424. https://doi.org/10.1109/tcyb.2018.2857815
Guo HB, Sheng B, Li P, Chen CLP (2021) Multiview high dynamic range image synthesis using fuzzy broad learning system. IEEE Trans Cybern 51(5):2735–2747. https://doi.org/10.1109/TCYB.2019.2934823
Jin JW, Liu ZL, Chen CLP (2018) Discriminative graph regularized broad learning system for image recognition. Sci China-Inform Sci 61(11):112209. https://doi.org/10.1007/s11432-017-9421-3
Zhao HM, Zheng JJ, Deng W, Song YJ (2020) Semi-supervised broad learning system based on manifold regularization and broad network. IEEE Trans Circuit Syst I-Regular Papers 67(3):983–994. https://doi.org/10.1109/tcsi.2019.2959886
Feng SB, Ren WJ, Han M, Chen YW (2019) Robust manifold broad learning system for large-scale noisy chaotic time series prediction: a perturbation perspective. Neural Netw 117:179–190. https://doi.org/10.1016/j.neunet.2019.05.009
Zheng YF, Chen BD, Wang SY, Wang WQ (2021) Broad learning system based on maximum Correntropy criterion. IEEE Trans Neural Networks Learn Syst 32(7):3083–3097. https://doi.org/10.1109/TNNLS.2020.3009417
Chu F, Liang T, Chen CLP, Wang XS, Ma XP (2020) Weighted broad learning system and its application in nonlinear industrial process modeling. IEEE Trans Neural Networks Learn Syst 31(8):3017–3031. https://doi.org/10.1109/TNNLS.2019.2935033
Liu ZL, Chen CLP, Feng S, Feng QY, Zhang T (2021) Stacked broad learning system: from incremental flatted structure to deep model. IEEE Trans Syst, Man, Cybernetics: Syst 51(1):209–222. https://doi.org/10.1109/TSMC.2020.3043147
Xu ML, Han M, Chen CLP, Qiu T (2020) Recurrent broad learning Systems for Time Series Prediction. IEEE Trans Cybern 50(4):1405–1417. https://doi.org/10.1109/tcyb.2018.2863020
Han M, Feng SB, Chen CLP, Xu ML, 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
Han M, Li WJ, Feng SB, Qiu T, Chen CLP (2021) Maximum information exploitation using broad learning system for large-scale chaotic time-series prediction. IEEE Trans Neural Networks Learn Syst 32(6):2320–2329. https://doi.org/10.1109/TNNLS.2020.3004253
Pu XK, Li CG (2021) Online semi-supervised broad learning system for industrial fault diagnosis. IEEE Trans Industrial Inform 17(10):6644–6654. https://doi.org/10.1109/TII.2020.3048990
Wang BS, Zhao Y, Chen CLP (2021) Hybrid transfer learning and broad learning system for wearing mask detection in the COVID-19 era. IEEE Trans Instrum Meas 70:5009612–5009612. https://doi.org/10.1109/TIM.2021.3069844
Sheng B, Li P, Zhang YH, Mao L, Chen CLP (2021) GreenSea: visual soccer analysis using broad learning system. IEEE Trans Cybernetics 51(3):1463–1477. https://doi.org/10.1109/TCYB.2020.2988792
Du J, Vong CM, Chen CLP (2021) Novel efficient RNN and LSTM-like architectures: recurrent and gated broad learning systems and their applications for text classification. IEEE Trans Cybernetics 51(3):1586–1597. https://doi.org/10.1109/TCYB.2020.2969705
Gao S, Guo G, Chen CLP (2019) Event-based incremental broad learning system for object classification. In: 2019 IEEE/CVF international conference on computer vision workshop (ICCV). Seoul, Korea (South), pp 2989–2998
Huang GB (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cogn Comput 6(3):376–390. https://doi.org/10.1007/s12559-014-9255-2
Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2011) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1–122. https://doi.org/10.1561/2200000016
Tropp JA, Gilbert AC (2007) Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans Inf Theory 53(12):4655–4666. https://doi.org/10.1109/TIT.2007.909108
Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. Siam J Imaging Sci 2(1):183–202. https://doi.org/10.1137/080716542
Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20(3):273–297. https://doi.org/10.1023/A:1022627411411
Suykens J, Gestel TV, Brabanter JD, Moor BD, Vandewalle J (2002) Least squares support vector machines. World Scientific Publishing Co. Pte. Ltd., Singapore
Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybernetics Part B: Cybern 42(2):513–529. https://doi.org/10.1109/tsmcb.2011.2168604
Xie RS, Wang ST (2020) Downsizing and enhancing broad learning systems by feature augmentation and residuals boosting. Complex Intell Syst 6:411–429. https://doi.org/10.1007/s40747-020-00139-2
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507. https://doi.org/10.1126/science.1127647
Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning (ICML). Helsinki, Finland, pp 1096–1103
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
Salakhutdinov R, Hinton GE (2009) Deep Boltzmann Machines. J Mach Learn Res 5(2):1967–2006
Bishop CM (2006) Pattern recognition and machine learning (information science and statistics). Springer-Verlag, New York, NY, USA
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th international conference on neural information processing systems (NIPS) - volume 1. Lake Tahoe, Nevada, USA, pp 1106–1114
Shuang F, Chen CLP (2018) A fuzzy restricted Boltzmann machine: novel learning algorithms based on the crisp Possibilistic mean value of fuzzy numbers. IEEE Trans Fuzzy Syst 26(1):117–130. https://doi.org/10.1109/TFUZZ.2016.2639064
Kasun LLC, Zhou H, Huang GB, Vong CM (2013) Representational learning with ELMs for big data. IEEE Intell Syst 28(6):31–34
Tang J, Deng C, Huang GB (2016) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Networks Learn Syst 27(4):809–821. https://doi.org/10.1109/TNNLS.2015.2424995
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). Seattle, USA, pp. 770–778
Zhang T, Chen R, Yang X, Guo S (2019) Rich feature combination for cost-based broad learning system. IEEE Access 7:160–172. https://doi.org/10.1109/ACCESS.2018.2885164
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
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
Mao R, Cui R, Chen CLP (2021) Broad learning with reinforcement learning signal feedback: theory and applications. IEEE Trans Neural Networks Learn Syst Early access:1–13. https://doi.org/10.1109/TNNLS.2020.3047941
Sabour S, Frosst N, Hinton G (2017) Dynamic routing between capsules. Adv Neural Inf Proces Syst 30:3856–3866
Choi J, Seo H, Im S, Kang M (2019) Attention routing between capsules. In: 2019 IEEE/CVF international conference on computer vision workshop (ICCV). Seoul, Korea (South), pp 1981–1989. https://doi.org/10.1109/ICCVW.2019.00247
Huang W, Zhou F (2020) DA-CapsNet: dual attention mechanism capsule network. Sci Rep 10:11383. https://doi.org/10.1038/s41598-020-68453-w
Ribeiro F, Leontidis G, Kollias S (2020) Capsule routing via variational bayes. AAAI. New York, USA, In, pp 3749–3756
Mazzia V, Salvetti F, Chiaberge M (2021) Efficient-CapsNet: capsule network with self-attention routing. Sci Rep 11:14634. https://doi.org/10.1038/s41598-021-93977-0
Zhang L, Li J, Lu G, Shen P (2022) Analysis and variants of broad learning system. IEEE Trans Syst, Man, Cybernetics: Syst 52(1):334–344. https://doi.org/10.1007/s00371-020-01796-7
Quan Q, He F, Li H (2021) A multi-phase blending method with incremental intensity for training detection networks. Vis Comput 37(2):245–259. https://doi.org/10.1007/s00371-020-01796-7
Zhang S, He F (2020) DRCDN: learning deep residual convolutional Dehazing networks. Vis Comput 36(9):1797–1808. https://doi.org/10.1007/s00371-019-01774-8
Chen Y, He F, Li H, Zhang D, Wu Y (2020) A full migration BBO algorithm with enhanced population quality bounds for multimodal biomedical image registration. Appl Soft Comput 93:106335. https://doi.org/10.1016/j.asoc.2020.106335
Li H, He F, Chen Y, Pan Y (2021) MLFS-CCDE: multi-objective large-scale feature selection by cooperative coevolutionary differential evolution. Memetic Comput 13(1):1–18. https://doi.org/10.1007/s12293-021-00328-7
Acknowledgments
This work is supported by the National Natural Science Foundation of China (Grant No. 61603326), the research fund of Jiangsu Provincial Key Constructive Laboratory for Big Data of Psychology and Cognitive Science (Grant No. 72591962004G, 72591862007G).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised: There was a mistake in Tables 8, 10 and Algorithm 1.
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
Guo, W., Chen, S. & Yuan, X. H-BLS: a hierarchical broad learning system with deep and sparse feature learning. Appl Intell 53, 153–168 (2023). https://doi.org/10.1007/s10489-022-03498-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03498-0