Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture
The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.
Abstract
Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“They show that our method instantiated with Fast R-CNN and Faster R-CNN outperforms the approach based on knowledge distillation [53] consistently, in terms of both the final performance and the performance drop compared with the upper bounds.”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“The gap between the solid lines is almost always larger than that of the dashed lines, which means our mAP drop is consistently less than ILOD [8].”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“it still suffers from catastrophic forgetting when directly applied to object detection as reported in [8].”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“our results surpass the previous best [8], [21], [22], [23] in terms of both the final performance and the performance gap compared with the joint training upper bound.”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
In the citing paper
“Compared with ILOD [8], our IncDet achieves much less performance drop in both in-dataset and cross-dataset scenarios.”
From IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2021) · cites this paper as [8]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Common approaches, which have the advantage of easy implementation and outstanding efficiency, for feature selection include variable ranking [28], feature subset selection [29], penalized least squares [30], random feature extractions such as nonadaptive random projections [31] and random forest [32], or convolution-…”
BackgroundVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“2716952 the most popular deep networks are the deep belief networks (DBN) [5], [6], the deep Boltzmann machines (DBM) [7], and the convolutional neural networks (CNN) [8], [9].”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 6×
“Specifically, if the function in the feature mapping uses convolutional functions, the broad learning network structure is very similar to that of classical CNN structure except that the broad learning network has additional connecting links between the convolutional layers and the output layer.”
BackgroundMethodInfluentialGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 7×
“2716952 the most popular deep networks are the deep belief networks (DBN) [5], [6], the deep Boltzmann machines (DBM) [7], and the convolutional neural networks (CNN) [8], [9].”
BackgroundInfluentialRegression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“The above problem denoted by lasso in [45] is convex.”
BackgroundReducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
A fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 6×
“Parameters of RBM are referred to [5], i.”
BackgroundMethodInfluentialBoyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,677
A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Beck, A., & Teboulle, M. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080716542 · Cited by 11,952 · cited 2×
“Moreover, it has been shown that many state-of-art algorithms for l1 norm involved problems could be derived by ADMM [50], such as FISTA.”
Research works printed but not linked: 2
- serre, 2002, Matrices, Theory and Applications
- goodfellow, 2016, Deep Learning
Cited by
Items 301–400 of 1,000
Nazir, A., Cheema, M. N., Sheng, B., Li, P., Kim, J., & Lee, T. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3050310 · Cited by 34
“constructed model should be adaptive for new data to cope with the problem of insufficient features for required output [16].”
BackgroundDeep Learning of Two-Phase Flow in Porous Media via Theory-Guided Neural Networks
Li, J., Zhang, D., Wang, N., & Chang, H. (2021) · SPE Journal · doi:10.2118/208602-pa · Cited by 33
Wang, D., & Yang, S. X. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109970 · Cited by 33
“Broad Learning System (BLS) is an efficient incremental learning system without deep structures, which is proposed by Professor Chen of the University from Macau university in 2018 [27].”
BackgroundFast remodeling for nonlinear distortion mitigation based on transfer learning
Zhang, J., Xia, L., Zhu, M., Hu, S., Xu, B., & Qiu, K. (2019) · Optics Letters · doi:10.1364/ol.44.004243 · Cited by 33
A Broad Learning Aided Data-Driven Framework of Fast Fault Diagnosis for High-Speed Trains
Chen, H., Jiang, B., & Ding, S. X. (2020) · IEEE Intelligent Transportation Systems Magazine · doi:10.1109/mits.2019.2907629 · Cited by 33
A Real-Time Adaptive Fault Diagnosis Scheme for Dynamic Systems With Performance Degradation
He, X. Y., Li, C., & Liu, Z. (2023) · IEEE Transactions on Reliability · doi:10.1109/tr.2023.3324539 · Cited by 33
Self-citationDeng, W., Shen, J., Ding, J., & Zhao, H. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3545741 · Cited by 42
Adaptive Broad Network With Graph-Fuzzy Embedding for Imbalanced Noise Data
Chen, W., Yang, K., Yu, Z., Nie, F., & Chen, C. L. P. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3543369 · Cited by 32
Self-citationXu, Y., Yu, Z., Cao, W., Chen, C. L. P., & You, J. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2961076 · Cited by 34
“(ELM) [25], [26], broad learning system (BLS) [27].”
MethodSelf-citationGao, X., Bai, W., Li, T., Yuan, L., & Long, Y. (2021) · Nonlinear Dynamics · doi:10.1007/s11071-021-06634-6 · Cited by 32
Huang, J., Vong, C.-M., Chen, C. L. P., & Zhou, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3165299 · Cited by 34
“BLS [29] is an improved sequel of RVFLNN with the sparse encoder and dynamic increasingly update algorithm for classification or regression tasks.”
BackgroundMethodSelf-citationAutomated layer-wise solution for ensemble deep randomized feed-forward neural network
Hu, M., Gao, R., Suganthan, P. N., & Tanveer, M. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.148 · Cited by 34
Yin, F., Li, W., Zhang, K., Wang, J., & Pal, N. R. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119648 · Cited by 31
Abdi‐Sargezeh, B., Shirani, S., Sanei, S., Took, C. C., Geman, O., Alarcón, G., & Valentín, A. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107782 · Cited by 41
Hybrid Ensemble Broad Learning System for Network Intrusion Detection
Lin, M., Yang, K., Yu, Z., Shi, Y., & Chen, C. L. P. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3332957 · Cited by 33
“Thepseudoinversecalculationhasbeenrigorouslyproved theoreticallyin[10].”
MethodResultSelf-citationWen, Y., Liu, X., & Yu, H. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111636 · Cited by 42
Near-Surface Rayleigh Wave Dispersion Curve Inversion Algorithms: A Comprehensive Comparison
Yang, X.-H., Zhou, Y., Han, P., Feng, X., & Chen, X. (2024) · Surveys in Geophysics · doi:10.1007/s10712-024-09826-y · Cited by 32
“Although the deep learning network possesses powerful modeling capability, it suffers from the disadvantage of time-consuming network training (Chen and Liu 2017; Kuok and Yuen 2020; Wang et al. 2022b; Zhou et al. 2022).”
Microservice-based digital twin system towards smart manufacturing
Yang, H., Jiang, G., Tian, W., Mei, X., Nee, A. Y. C., & Ong, S. K. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102858 · Cited by 37
Tian, H., Tang, J., Aljerf, L., Wang, T., & Qiao, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127530 · Cited by 31
Kernel Regularized Nonlinear Dictionary Learning for Sparse Coding
Liu, H., Liu, H., Sun, F., & Fang, B. (2017) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2736248 · Cited by 31
“4) Though we adopt the SAE network in our framework for training, this idea can be easily extended to other deep learning methods, such as No-Prop extreme learning machine [21], [26], [36], [37] and broad learning [27] for more complicated scenarios.”
BackgroundMethodDistributed Algorithms for Average Consensus of Input Data With Fast Convergence
Xie, K., Cai, Q., Zhang, Z., & Fu, M. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2914385 · Cited by 31
“role in wider applications, including distributed sensing and fusion [18], distributed optimization [19]–[22], and machine learning [23], [24].”
BackgroundGuo, J., Li, M., Wang, L., Yang, B., Zhang, L., Chen, Z., Han, S., García‐Hernández, L., & Abraham, A. (2019) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2019.103378 · Cited by 32
Deep Neural Networks with Broad Views for Parkinson's Disease Screening
Zhang, X., Yang, Y. Z., Wang, H., Ning, S., & Wang, H. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983000 · Cited by 31
CNN-Based Broad Learning for Cross-Domain Emotion Classification
Zeng, R., Liu, H., Peng, S., Cao, L., Yang, A., Zong, C., & Zhou, G. (2022) · Tsinghua Science & Technology · doi:10.26599/tst.2022.9010007 · Cited by 31
“(3) Broad learning As a flat network, BL [23] has many advantages, such as simple structure, short training time, and good generalization performance, which has become an alternative solution for deep learning.”
BackgroundSafe Semi-Supervised Extreme Learning Machine for EEG Signal Classification
She, Q., Hu, B., Gan, H., Fan, Y., Nguyen, T. P., Potter, T. B. H., & Zhang, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2868713 · Cited by 31
KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild
Zhang, Y., Bai, Y., Ding, M., Xu, S., & Ghanem, B. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3004819 · Cited by 36
“With the development of deep convolutional neural networks (DCNNs) [11]–[15], pedestrian detection has been extensively studied and huge progress has been made over the past few years.”
BackgroundBGRF: A broad granular random forest algorithm
Fu, X., Chen, Y., Yan, J., Chen, Y., & Xu, F. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-223960 · Cited by 44
“In 2018, Chen [35] et al. proposed a broad learning system and designed a planar network.”
Twin Broad Learning System for Fault Diagnosis of Rotating Machinery
Yang, L., Yang, Z., Song, S., Li, F., & Chen, C. L. P. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3259022 · Cited by 39
“To avoid the high computational costs yet keep the strong learning ability at the same time, recent research proposes a novel single-layer feedforward network (SLFN) architecture, named broad learning system (BLS) [12], which provides an alternative way for using deep models.”
BackgroundMethodSelf-citationLou, S., Yang, C., Kong, L., Lin, T., Zhang, H., Wu, P., & Chai, L. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3487776 · Cited by 30
Transductive Transfer Learning Based on Broad Learning System
Yang, L., Song, S., & Chen, C. L. P. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00162 · Cited by 30
“Three standard classifiers are tested in the experiments, including support vector machine (SVM)1 [24], extreme learning machine (ELM) [15] and broad learning system (BLS) [17].”
BackgroundMethodSelf-citationComparison of Machine Learning Algorithms for Detection of Network Intrusions
Li, Z., Batta, P., & Trajković, L. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00719 · Cited by 34
“The Broad Learning System (BLS) [15], an alternative to deep learning networks, offers desired classification accuracy with shorter training time when using the Modified National Institute of Standards and Technology (MNIST) [16] and the New York University Object Recognition Benchmark [17] datasets.”
BackgroundMethodInfluentialIncremental Wishart Broad Learning System for Fast PolSAR Image Classification
Fan, J., Wang, X., Wang, X., Zhao, J., & Liu, X. (2019) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2913999 · Cited by 30
“According to ridge regression learning theory [15], the optimal W (O) can be obtained through”
BackgroundInfluentialJiang, S. B., Wong, P. K., & Liang, Y. C. (2019) · IEEE Access · doi:10.1109/access.2019.2950240 · Cited by 33
“For Broad Learning [13], the regularization parameter λ of the ridge regression is set to 1×10∧(−8).”
BackgroundMethodA Construction of Robust Representations for Small Data Sets Using Broad Learning System
Tang, H., Dong, P., & Shi, Y. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2957818 · Cited by 31
“The broad learning system (BLS), proposed by Chen and Liu [32], is a flatted and incremental learning neural network.”
BackgroundMethodInfluentialA Hybrid Recursive Implementation of Broad Learning With Incremental Features
Liu, D., Baldi, S., Yu, W., & Chen, C. L. P. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3043110 · Cited by 30
“Extensive experiments on the MNIST data set have been performed in [29], and the MATLAB source codes of the BLS used in that article can be downloaded from the website of Prof.”
BackgroundMethodInfluentialSelf-citationMonitoring multi-domain batch process state based on fuzzy broad learning system
Peng, C., & Chunhao, D. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115851 · Cited by 36
Randomized neural networks for multilabel classification
Chauhan, V., & Tiwari, A. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.108184 · Cited by 30
Baggage Threat Recognition Using Deep Low-Rank Broad Learning Detector
Velayudhan, D., Hassan, T., Ahmed, A. H., Damiani, E., & Werghi, N. (2022) · IEEE Mediterranean Electrotechnical Conference (MELECON) · doi:10.1109/melecon53508.2022.9842976 · Cited by 30
Adaptive Ensemble Clustering With Boosting BLS-Based Autoencoder
Shi, Y., Yang, K., Yu, Z., Chen, C. L. P., & Zeng, H. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3271120 · Cited by 30
“In this section, we mainly introduce the basic concept of broad learning system (BLS) [34] and BLS-based autoencoder (BLSAE) [35].”
BackgroundMethodSelf-citationBroad Learning System for Control of Nonlinear Dynamic Systems
Feng, S., & Chen, C. L. P. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00383 · Cited by 30
“The Broad Learning System (BLS) [26] is a novel structure established based on the random vector functional-link neural network (RVFLNN) [27] which inherits its major feature, and it can be expanded in a wide sense.”
BackgroundSelf-citationFault Diagnosis for Power Converters Based on Incremental Learning
Zhang, S., Wang, R., Wang, L., Si, Y., Lin, A., & Wang, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3265095 · Cited by 41
“The proposed model builds on the automatic feature extraction of a deep residual network (ResNet) and the incremental learning capabilities of the broad learning system (BLS) [21], [22], [23].”
MethodZhang, Y., Kong, X., Wang, J., Wang, S., Zhao, Z., & Wang, F. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107479 · Cited by 34
Hu, J. Z., Wu, M., Cao, W., & Pedrycz, W. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3359444 · Cited by 34
Wang, T., Tang, J., Aljerf, L., Qiao, J., & Alajlani, M. M. (2024) · Fuel · doi:10.1016/j.fuel.2024.133382 · Cited by 31
Hu, J. Z., Wu, M., Chen, L., & Pedrycz, W. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3076208 · Cited by 29
State-of-the-Art Development of Complex Systems and Their Simulation Methods
Tang, Y., Li, L., & Liu, X. (2021) · Complex System Modeling and Simulation · doi:10.23919/csms.2021.0025 · Cited by 36
“Moreover, in 2009, Cao et al.[29] proposed the concepts of M-Interaction, M-Space, and M-Computing, which are the three key components for studying OCGSs and constructing problem-solving systems.”
BackgroundMethodInfluentialA new data augmentation method for EEG features based on the hybrid model of broad-deep networks
Fu, R., Wang, Y., & Jia, C. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117386 · Cited by 31
Gu, K., Liu, H., Liu, J., Yu, X., Shi, T., & Qiao, J. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3157365 · Cited by 38
Interpolation-based virtual sample generation for surface roughness prediction
Tian, W., Zhang, J., Zhao, F., Feng, X., Mei, X., Chen, G., & Wang, H. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-022-02054-4 · Cited by 29
“…fusion of process parameters and sensor signal features(Lu,2008;Özel&Karpat,2005;Salgadoetal.,2009; Samanta, 2009; Grzenda & Bustillo, 2013; Chen et al., 2017; Huanget al., 2019; Tianet al., 2022a,b), anddirect useof sensor signals (Plaza & López, 2018a,b; Rifai et al., 2020; Pan et al.,…”
Model Predictive Control of Magnetic Helical Swimmers in Two-Dimensional Plane
Liu, J., Xu, T., & Wu, X. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3250701 · Cited by 29
“This paper designs a neural network architecture based on BLS [36], which builds an adaptive compensating update model to figure out the problem.”
MethodDu, K.-L., Zhang, R., Jiang, B., Zeng, J., & Lu, J. (2025) · Mathematics · doi:10.3390/math13030451 · Cited by 45
Zhu, L., Lian, C., Zeng, Z., & Su, Y. (2019) · Cognitive Computation · doi:10.1007/s12559-019-09698-0 · Cited by 28
Detecting Internet Worms, Ransomware, and Blackouts Using Recurrent Neural Networks
Li, Z., Rios, A. L. G., & Trajković, L. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283472 · Cited by 28
“BGP anomalies [13], [14] may be classi-fied using various machine learning algorithms such as support vector machine [15], recurrent neural networks (RNNs), and broad learning system [16].”
MethodSemisupervised Classification of Hyperspectral Image Based on Graph Convolutional Broad Network
Wang, H., Cheng, Y., Chen, C. L. P., & Wang, X. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3062642 · Cited by 29
Self-citationHealth Management of Dry-Type Transformer Based on Broad Learning System
Ge, Q., Wang, M., Jiang, H., Lu, Z., Yao, G., & Sun, C. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3065616 · Cited by 28
Broad learning system with manifold regularized sparse features for semi-supervised classification
Huang, S., Liu, Z., Jin, W., & Mu, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.052 · Cited by 28
Self-citationEnsemble Strategy Utilizing a Broad Learning System for Indoor Fingerprint Localization
Wu, C., Qiu, T., Zhang, C., Qu, W., & Wu, D. O. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3097511 · Cited by 28
Yang, Y., Huang, Q., & Li, P. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117184 · Cited by 28
Yang, Z., Li, S., Yu, D., & Chen, C. L. P. (2022) · Nonlinear Dynamics · doi:10.1007/s11071-022-07505-4 · Cited by 28
Self-citationShen, H., Wang, X., Duan, P., Cao, J., & Wang, J. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3195781 · Cited by 28
Peng, S., Zeng, R., Cao, L., Yang, A., Niu, J., Zong, C., & Zhou, G. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110173 · Cited by 32
“BL was presented by Chen and Liu [10], which includes feature mapping nodes and enhancement nodes in a wide manner, instead of stacking and deeply expand neurons.”
Huang, J., Vong, C., Wang, G., Qian, W., Zhou, Y., & Chen, C. L. P. (2023) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2023.3249192 · Cited by 28
Self-citationBroad Learning Autoencoder With Graph Structure for Data Clustering
Yu, Z., Zhong, Z., Yang, K., Cao, W., & Chen, C. L. P. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3283425 · Cited by 32
Self-citationWear Fault Diagnosis of Aeroengines Based on Broad Learning System and Ensemble Learning
Wang, M., Ge, Q., Jiang, H., & Yao, G. (2019) · Energies · doi:10.3390/en12244750 · Cited by 28
“The establishment of BLS is as follows [35].”
BackgroundInfluentialResearch on Transfer Learning of Vision-based Gesture Recognition
Wu, B., Yang, C., & Zhong, J. (2021) · Machine Intelligence Research · doi:10.1007/s11633-020-1273-9 · Cited by 28
Shan, W., Li, D., Liu, S., Song, M.-M., Xiao, S.-G., & Zhang, H.-L. (2024) · Expert systems with applications · doi:10.1016/j.eswa.2024.124902 · Cited by 25
Ensemble Denoising Autoencoders Based on Broad Learning System for Time-Series Anomaly Detection
Lin, Y., Yu, Z., Yang, K., & Chen, C. L. P. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3548941 · Cited by 30
“In recent years, the broad learning system (BLS) [9] has attracted significant attention for its remarkable performance in diverse applications [10], [11], [12], [13].”
Self-citationDa-Zhong, M., Wang, J., Sun, Q., & Hu, X. (2019) · IEEE Access · doi:10.1109/access.2019.2908015 · Cited by 28
“Broad learning system (BLS) aims to offer an alternative way of learning in deep structure [24], [25].”
BackgroundA CNN-Based Broad Learning System
Yang, F. (2018) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/compcomm.2018.8780984 · Cited by 30
“Broad Learning System (BLS) [8] offers an alternative way of machine learning in deep structure.”
BackgroundMoving Cast Shadows Segmentation Using Illumination Invariant Feature
Wang, B., Zhao, Y. J., & Chen, C. L. P. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2954752 · Cited by 27
“In addition, there are many other methods, such as edge based [29], [30], statistic based [31]–[33], single image based [34]–[37], multiple features based [38]–[40], and other features [41]–[44], or techniques [45]–[50] proposed to address the problematic situations.”
BackgroundSelf-citationVB-Net: Voxel-Based Broad Learning Network for 3D Object Classification
Liu, Z., Song, W., Tian, Y., Ji, S., Sung, Y., Wen, L., Zhang, T., Song, L., & Gozho, A. (2020) · Applied Sciences · doi:10.3390/app10196735 · Cited by 32
“In recent years, Chen et al. introduced a new neural network structure called the broad learning system [11].”
BackgroundMethodInfluentialSelf-citationFrequency Principle in Broad Learning System
Chen, G., Gan, M., Chen, C. L. P., Zhu, H., & Chen, L. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3081568 · Cited by 30
“where αi,l ∈ Z is the frequency index and ρ is the frequency range, which is set to [1, 40] and [0, 20π] in our experiments.”
BackgroundMethodInfluentialSelf-citationJin, Y., Sheng, B., Li, P., & Chen, C. L. P. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3004634 · Cited by 27
“where B can be calculated by the additional enhanced node Hm+1 and the original input nodes Fn (see the detail in [30]).”
BackgroundInfluentialSelf-citationNakhodchi, S., Zolfaghari, B., Yazdinejad, A., & Dehghantanha, A. (2021) · Conference on Privacy, Security and Trust · doi:10.1109/pst52912.2021.9647777 · Cited by 27
Wang, J., Xie, Y., Xie, S., & Chen, X. (2022) · ISA Transactions · doi:10.1016/j.isatra.2022.06.039 · Cited by 28
Double-kernelized weighted broad learning system for imbalanced data
Chen, W., Yang, K., Zhang, W., Shi, Y., & Yu, Z. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07534-5 · Cited by 27
“The literature [20] mathematically demonstrates that BLS has a general learning approximation capability.”
BackgroundGuo, L., Li, R., & Jiang, B. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3172896 · Cited by 27
“The BLS model is first proposed by Chen and Liu [34]; it achieves superior generalization performance and remarkable computational reduction, which inherits from random vector functional-like neural networks [35].”
BackgroundMethodInfluentialPeng, C., Bao, X., Meng, F., & Lu, R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119193 · Cited by 27
Men, J., & Zhao, C. M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121159 · Cited by 30
An incremental photovoltaic power prediction method considering concept drift and privacy protection
Zhang, L., Zhu, J., Zhang, D., & Liu, Y. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.121919 · Cited by 35
Fuzzy logic interpretation of quadratic networks
Fan, F., & Wang, G. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.09.001 · Cited by 29
Zhang, C., Peng, K., & Dong, J. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114166 · Cited by 27
Fu, Y., Cao, H., Chen, X., & Ding, J. (2022) · ISA Transactions · doi:10.1016/j.isatra.2022.10.014 · Cited by 27
Cross-domain knowledge transfer in industrial process monitoring: A survey
Chai, Z., Zhao, C., & Huang, B. (2025) · Journal of Process Control · doi:10.1016/j.jprocont.2025.103408 · Cited by 33
Ryan, L., & Agaian, S. С. (2025) · Bioengineering · doi:10.3390/bioengineering12060639 · Cited by 28
Sparse Bayesian Broad Learning System for Probabilistic Estimation of Prediction
Xu, L., Chen, C. L. P., & Han, R. (2020) · IEEE Access · doi:10.1109/access.2020.2982214 · Cited by 26
“= [ 0 1 ]”
BackgroundMethodInfluentialSelf-citationMulti-View Broad Learning System for Primate Oculomotor Decision Decoding
Shi, Z., Chen, X., Zhao, C., He, H., Stuphorn, V., & Wu, D. (2020) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2020.3003342 · Cited by 27
“BLS has achieved comparable performance, with much less computational cost, with deep learning approaches on two single-view image datasets [5].”
BackgroundMethodInfluentialDeep-broad Learning System for Traffic Flow Prediction toward 5G Cellular Wireless Network
Chen, M., Wei, X., Gao, Y., Huang, L., Chen, M., & Kang, B. (2020) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc48107.2020.9148092 · Cited by 29
“[11] tried to propose another efficient and effective learning capability”
BackgroundFault Diagnosis of Sucker Rod Pump Based on Deep-Broad Learning Using Motor Data
Wei, J., & Gao, X. (2020) · IEEE Access · doi:10.1109/access.2020.3036078 · Cited by 27
“[17] T. Han, C. Liu, W. Yang, and D. Jiang, ‘‘Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application,’’ ISA Trans., vol. 97, pp. 269–281, Feb. 2020.”
BackgroundInfluentialYu, W., & Zhao, C. (2021) · Journal of Process Control · doi:10.1016/j.jprocont.2021.09.014 · Cited by 26
Graph-based sparse bayesian broad learning system for semi-supervised learning
Xu, L., Chen, C. L. P., & Han, R. (2022) · Information Sciences · doi:10.1016/j.ins.2022.03.037 · Cited by 26
Self-citationWang, P., Yin, Y., Bai, W. Y., Deng, X., & Shao, W. (2022) · Chemical Engineering Science · doi:10.1016/j.ces.2022.117753 · Cited by 26
Towards Broad Learning Networks on Unmanned Mobile Robot for Semantic Segmentation
Li, J., Dai, Y., Wang, J., Su, X., & Ma, R. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812204 · Cited by 29
Automated broad transfer learning for cross-domain fault diagnosis
Liu, G., Shen, W., Gao, L., & Kusiak, A. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.11.003 · Cited by 28
Misbehavior detection in intelligent transportation systems based on federated learning
Campos, E. M., Hernández-Ramos, J. L., González-Vidal, A., Baldini, G., & Skármeta, A. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101127 · Cited by 37
An End-to-End Broad Learning System for Event-Based Object Classification
Gao, S., Guo, G., Huang, H., Cheng, X., & Chen, C. L. P. (2020) · IEEE Access · doi:10.1109/access.2020.2978109 · Cited by 30
“The Broad Learning System (BLS) [9] is a novel structure established based on the random vector functional-link neural network (RVFLNN) [42] which inherits features, and can be expanded substantially.”
BackgroundMethodInfluentialSelf-citationZhou, Q., & Niu, Y. (2024) · Advanced Intelligent Systems · doi:10.1002/aisy.202300853 · Cited by 29
Xu, K., He, T., Yang, P., Meng, X.-B., Zhu, C., & Jin, X. (2024) · Energy · doi:10.1016/j.energy.2024.132920 · Cited by 26
Combining CNN and Broad Learning for Music Classification
Tang, H., & Chen, N. (2020) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2019edp7175 · Cited by 27
“To solve these problems, a hybrid architecture-based music classification scheme, which takes full advantage of the merits of RCNN [19] in representing the nonlinear property and inherent hierarchical nature of music, and that of Broad Learning (BL) in ensuring training efficiency [20], is proposed in this paper.”
MethodZhang, X., Nojima, Y., Ishibuchi, H., Hu, W., & Wang, S. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2999813 · Cited by 26
“…their direct use for prediction in EP-TSK-FK, we take the traditional classi-fiers, i.e., two fuzzy classifiers (zero-order-TSK-FC [28], and first-order-TSK-FC [2], [11]), and two state-of-the-art classi-fiers (deep belief networks (DBN) [36] and Broad Learning Systems (BLS) [37]–[39]) for comparison.”
Background
Metadata
- Authors
- Chen, C. L. P., & Liu, Z.
- Affiliations
- Chinese Academy of Sciences (CN)
- University of Macau (MO)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2018-01
- Volume
- 29
- Issue
- 1
- Pages
- 10-24
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2738226240
- Cited by
- 1,957
- References
- 58
- Citations by year
- 2026: 177 · 2025: 312 · 2024: 303 · 2023: 255 · 2022: 270 · 2021: 223 · 2020: 177 · 2019: 158 · 2018: 73
- FWCI
- 68.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Fundo para o Desenvolvimento das Ciências e da Tecnologia (019/2015/A1)
- UM Research Grants
- National Nature Science Foundation of China (61572540)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- broad learning system, incremental learning, flat network architecture, network expansion, model reduction, singular value decomposition, object recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.