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 801–900 of 1,000
Enhanced high‐order information extraction for multiphase batch process fault monitoring
Chunhao, D., Peng, C., & Kang, O. (2020) · The Canadian Journal of Chemical Engineering · doi:10.1002/cjce.23763 · Cited by 10
How Powerful are Shallow Neural Networks with Bandlimited Random Weights?Preprint
Li, M., Sonoda, S., Cao, F., Wang, Y. G., & Liang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.08427 · Cited by 10
“The framework of a broad learning system (Chen & Liu, 2017) performs in the manner of a flat network, in which the original inputs are transferred and placed as the “mapped features” in feature nodes and the structure is expanded in a wide sense in the “enhancement nodes.””
BackgroundQuasi-Equivalence of Width and Depth of Neural NetworksPreprint
Fan, F., Lai, R., & Wang, G. (2020) · Research Square · doi:10.21203/rs.3.rs-92324/v1 · Cited by 11
“Recently, the effects of width are discussed by more and more studies (Cheng et al., 2016; Chen and Liu, 2017; Zagoruyko and Komodakis, 2016).”
BackgroundWang, S., Yuen, K., Yang, X., & Zhang, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3266814 · Cited by 9
“Fortunately, the broad learning system (BLS) can overcome the above problems of DL models [47].”
BackgroundA realtime fingerprint liveness detection method for fingerprint authentication systems
Yuan, C., Zhang, Q., Wu, S., & Wu, Q. M. J. (2023) · Advances in computers · doi:10.1016/bs.adcom.2023.04.004 · Cited by 9
A highly efficient ADMM-based algorithm for outlier-robust regression with Huber loss
Wang, T., Lai, X., & Cao, J. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05370-9 · Cited by 9
“( As in extreme learning machines [42] and broad learning systems [43], the weight vectors and biases of the hidden nodes are randomly generated and then fixed during training.”
InfluentialZhang, Z., Zhang, D., & Wang, Y. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3390135 · Cited by 13
“However, there lacks a precise method to guide the selection of an optimal parameter setting [43].”
MethodBroad collaborative filtering with adjusted cosine similarity by fusing matrix completion
He, P., Shi, J., Ma, W., & Zheng, X. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112075 · Cited by 10
Hu, J. Z., Wu, M., & Witold Pedrycz, C. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3491101 · Cited by 10
“In order to overcome the above limitations, an effective architecture, called BLS [14], [15], has recently been developed.”
DHR-BLS: A Huber-type robust broad learning system with its distributed version
Zhang, Y., Ke, S., Li, J., Liu, W., Hu, J., & Yang, K. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113184 · Cited by 9
Chu, Y., Guo, Y. L., Ding, W., Cao, H., & Ping, P. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130337 · Cited by 9
Zhang, D., Sun, W., Kong, L., Yu, X., Wu, Y., & He, W. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3594597 · Cited by 9
“Initially introduced in [20], BLS distinguishes itself from traditional deep learning models by utilizing a wide architecture rather than relying on stacked hierarchical layers.”
Shahid, M. A., Zhang, X., Qin, X., & Peng, K. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae09c3 · Cited by 10
Simultaneous tool wear condition and surface roughness prediction under limited samples
Yang, H., Jiang, G., Tian, W., Mei, X., Nee, A. Y. C., & Ong, S. K. (2025) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2025.12.032 · Cited by 9
A constructive approach to data-driven randomized learning for feedforward neural networks
Dudek, G. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107797 · Cited by 9
Wind Speed Forecasting Based on a Hybrid EMD-BLS Method
Zhu, L., & Lian, C. (2019) · Chinese Automation Congress · doi:10.1109/cac48633.2019.8997269 · Cited by 9
“Chen CLP et al showed a new ANN: broad learning system (BLS) in 2018, [11].”
BackgroundClass mean‐weighted discriminative collaborative representation for classification
Gou, J., Song, J. P., Du, L., Zeng, S., Zhan, Y., & Zhang, Y. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22411 · Cited by 9
Prediction of yarn unevenness based on BMNN
Jiang, H., Song, J., Zhang, B., Zhao, S., & Wang, Y. (2021) · Journal of Engineered Fibers and Fabrics · doi:10.1177/15589250211037978 · Cited by 9
“Chen and Liu 20 designed BLS based on the idea of RVFLNN for the problem that deep architecture and learning require extremely time-consuming training processes.”
BackgroundZhang, J., Tian, W., Zhao, F., Mei, X., Chen, G., & Wang, H. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3204003 · Cited by 9
Gao, S., Guo, G., Huang, H., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3225180 · Cited by 9
“Because of its universal approximation properties, different various improvements and successful applications of FLNN were developed, such as the random vector functional-link network [25].”
InfluentialSelf-citationPrototype Enhancement-Based Incremental Evolution Learning for Urban Garbage Classification
Han, H., Fan, X., & Li, F. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3250207 · Cited by 12
A comprehensive review of motor movement challenges and rehabilitative robotics
Suppiah, R., Kim, N., Abidi, K., & Sharma, A. (2023) · Smart Health · doi:10.1016/j.smhl.2023.100402 · Cited by 11
A Sample Selection Method for Neural-Network-Based Rayleigh Wave Inversion
Yang, X.-H., Zu, Q., Zhou, Y., Han, P., & Chen, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3341955 · Cited by 9
“Based on the generation of the M N M and E N E , the only unknown variable, i.e., the network weighting matrix, can then be calculated by the following : Particularly, the Ridge regression of the pseudoinverse is applied for calculating the matrix W B [44].”
BackgroundMethodInfluentialWang, L.-E., Qi, Y., Sun, Z., & Li, X. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127277 · Cited by 10
Stacking multi-view broad learning system with residual structures for classification
Huang, T., Li, H., Zhou, G. L., & Li, S. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120559 · Cited by 10
Network Intrusion Detection Based on Deep Belief Network Broad Equalization Learning System
Deng, M., Sun, C., Kan, Y., Xu, H., Zhou, X., & Fan, S. (2024) · Electronics · doi:10.3390/electronics13153014 · Cited by 9
Yang, Y., Li, M., & Wang, L. (2024) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-024-03246-1 · Cited by 11
“…the feature set of the initial session is { F ( 1 ) , Y ( 1 ) } , in the feature mapping layer, F ( 1 ) first is mapped to K groups of feature nodes, which are computed by where 𝓁 ( ⋅ ) is the linear activation function, the randomly generated connection weight and bias W ( 1 ) Z and ( 1 ) Z [22].”
InfluentialVelayudhan, D., Ahmed, A. H., Hassan, T., Owais, M., Gour, N., Bennamoun, M., Damiani, E., & Werghi, N. (2024) · Visual Computing for Industry Biomedicine and Art · doi:10.1186/s42492-024-00182-7 · Cited by 9
“Alternatively, the broad learning system (BLS), introduced by Chen and Liu [29], maps input to a feature space using arbitrary weights, allowing faster training [30].”
Zhou, Q., Niu, Y., Xiang, W., & Zhao, L. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3514085 · Cited by 9
Optical reflection invariant-based method for moving shadows removal
Wang, B., & Chen, C. L. P. (2018) · Optical Engineering · doi:10.1117/1.oe.57.9.093102 · Cited by 9
Self-citationSparse Deep Tensor Extreme Learning Machine for Pattern Classification
Zhao, J. K., & Jiao, L. (2019) · IEEE Access · doi:10.1109/access.2019.2924647 · Cited by 9
A New Local Knowledge-Based Collaborative Representation for Image Recognition
Jin, J., Li, Y., Sun, L., Miao, J., & Chen, C. L. P. (2020) · IEEE Access · doi:10.1109/access.2020.2989452 · Cited by 9
“Image recognition, which aims to determine the labels of those query samples, has attracted the attention of many scholars in the machine learning community [1], [2].”
BackgroundSelf-citationImprovement of Neural-Network Classifiers Using Fuzzy Floating Centroids
Liu, S., Wang, L., Yang, B., Zhou, J., Chen, Z., & Dong, H. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2987904 · Cited by 9
Evolutionary-Based Weighted Broad Learning System for Imbalanced Learning
Zhang, T., Li, Y., & Chen, R. (2019) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske47853.2019.9170459 · Cited by 9
“Aside from its novel architectural design, the BLS also can be developed in an incremental learning algorithm which is suitable for broad expansion (refer to [6] for details), by doing so, the excessive parameters can be efficiently learned in a dynamic manner.”
BackgroundMethodKnowledge-Based Fuzzy Broad Learning Algorithm for Warning Membrane Fouling
Han, H., Zhang, Q., Liu, Z., & Qiao, J. (2020) · International Journal of Fuzzy Systems · doi:10.1007/s40815-020-00988-6 · Cited by 9
Self-citationYao, H., Zhang, Y., Wei, Y., & Tian, Y. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/8478016 · Cited by 9
“Recently, a new NNRW method, which broadly extends the hidden layer of RVFL called broad learning system, has been introduced [32, 33].”
MethodEffective Cancer Subtype and Stage Prediction via Dropfeature-DNNs
Chen, Z., Zhang, W., Deng, H., & Zhang, K. (2021) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2021.3058941 · Cited by 9
“The representation capability of DNNs can be reflected by the broad learning with a shallow architecture [49].”
BackgroundMultidomain Feature Fusion for Varying Speed Bearing Diagnosis Using Broad Learning System
Wu, T., Zhuang, Y., Fan, B., Guo, H., Fan, W., Yi, C., & Xu, K. (2021) · Shock and Vibration · doi:10.1155/2021/6627305 · Cited by 9
“BLS structure is shown in Figure 2 [30].”
BackgroundToward Deep Adaptive Hinging Hyperplanes
Tao, Q., Xu, J., Li, Z., Xie, N., Wang, S., Li, X., & Suykens, J. A. K. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3079113 · Cited by 9
“Except for MLP, we also compare with the broad learning (BL) network, which designs an incremental learning NN in a forwardwise way and has shown obviously better performance than PLN in both MNIST and NORB [35].”
BackgroundResultAn Incremental Clustering Algorithm with Pattern Drift Detection for IoT-Enabled Smart Grid System
Jiang, Z., Lin, R., & Yang, F. (2021) · Sensors · doi:10.3390/s21196466 · Cited by 12
Alzheimer’s disease classification from hippocampal atrophy based on PCANet-BLS
Liang, C., Lao, H., Wei, T., & Zhang, X. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12228-0 · Cited by 9
“in 2018 [7] based on the traditional random vector functional-link neural networks (RVFLNN), compared with the deep neural networks such as CNN, it has unique advantages in time consumption and solving nonlinear, small and medium sample problems.”
Zhou, Y., Li, X., Tang, Q., Kuok, S., Fei, K., & Gao, L. (2022) · Earth and Space Science · doi:10.1029/2021ea002043 · Cited by 9
“The transformation feature matrix, 𝐴𝐴 , can be calculated by the following formulas: where the 𝐴𝐴 𝐴𝐴 th mapped feature is computed by 𝐴𝐴 𝐴𝐴 𝑖𝑖 = 𝜙𝜙 ( 𝐒𝐒 𝑊𝑊 𝑓𝑓𝑖𝑖 + 𝛽𝛽 𝑓𝑓𝑖𝑖 ) ,𝑖𝑖 = 1 , 2 ,.. (Chen et al., 2018; Chen & Liu, 2017).”
BackgroundMethodInfluentialSelf-Growing Binary Activation Network: A Novel Deep Learning Model With Dynamic Architecture
Zhang, Z.-Y., Chen, Y., & Zhou, C. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3176027 · Cited by 11
“The proposed method, named self-growing binary activation network (SGBAN), was inspired by the gradual architecture growth proposed in [24]–[26], in which the training procedure was conducted with a small network and then progressively expanded until the whole architecture was constructed.”
MethodTuya (2022) · IEEE Access · doi:10.1109/access.2022.3201537 · Cited by 9
“Traditional machine learning methods include SVMCK [30] and ELMCK [31]; broad learning system methods include BLS [20], SBLS [22], LBP-BLS [23]; deep learning methods include GCN [10], SSGCN [16], MDGCN [18], 2DCNN [32], GCBN [33].”
BackgroundMethodZhang, S., & Xie, L. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110410 · Cited by 9
Wind Speed Prediction Based on VMD-BLS and Error Compensation
Jiao, X., Zhang, D., Song, D., Mu, D., Tian, Y., & Wu, H. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11051082 · Cited by 9
Intrusion detection of manifold regularized broad learning system based on LU decomposition
Liu, Y., Zhang, K., & Wang, Z. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05403-z · Cited by 10
“In early 2018, Chen proposed the Broad Learning System (BLS) [24], which is built based on Random Vector Functional-Linked Neural Network (RVFLNN).”
A Multiscale Concept Drift Detection Method for Learning from Data Streams
Wang, X., Kang, Q., Zhou, M., & Yao, S. (2018) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/coase.2018.8560554 · Cited by 9
Sitting Posture Recognition in Real-Time Combined with Index Map and BLS
Sun, W., Zhou, Z., & Li, H. (2019) · International Conference on Innovation in Artificial Intelligence (ICIAI) · doi:10.1145/3319921.3319955 · Cited by 9
“BROAD LEARNING SYSTEM Broad Learning System (BLS) [9-14] is a neural network structure that is different from the complex deep network structure.”
BackgroundZhang, Y., Gong, B., & Wang, Q. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.10.003 · Cited by 8
Fuzzy Broad Learning System Combined with Feature-Engineering-Based Fault Diagnosis for Bearings
Zhou, J., Yang, X., Liu, L., Wang, Y., Wang, J., & Hou, G. (2022) · Machines · doi:10.3390/machines10121229 · Cited by 8
An Incremental Broad-Learning-System-Based Approach for Tremor Attenuation for Robot Tele-Operation
Lai, G., Liu, W., Yang, W., Zhong, H., He, Y., & Zhang, Y. (2023) · Entropy · doi:10.3390/e25070999 · Cited by 9
Lithium-Ion Battery Capacity Prediction Method Based on Improved Extreme Learning Machine
Liu, Z., Huang, Z., Tang, L., & Wang, H. (2024) · Journal of Electrochemical Energy Conversion and Storage · doi:10.1115/1.4065095 · Cited by 9
Self-citationZhang, Y., Bai, Y., Jin, X., Zhao, Z., & Su, T. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108315 · Cited by 14
Secure and Efficient Continuous Learning Model for Traffic Flow Prediction
Le, J., Zhang, D., Yang, F., Xiang, T., & Liao, X. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3407959 · Cited by 8
“Broad learning (BL) model is first presented in the literature [26] in 2017, which is designed on a traditional random vector functional-link neural network (RVFLNN).”
BackgroundZhao, L., Xu, Z., Wang, G., & Huang, M. (2024) · Journal of Water Process Engineering · doi:10.1016/j.jwpe.2024.105534 · Cited by 8
Robust Unsupervised Anomaly Detection for Surface Defects Based on Stacked Broad Learning System
Wang, X., Bian, W., & Zhao, X. (2024) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2024.3465563 · Cited by 11
“TheBLSwasfirstproposedin 2018[17],whichenrichesthecontentofmachinelearningand expandstheformofthenetworkneuronstructures.”
InfluentialLiu, K., Zhao, X., & Hui, Y. (2024) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2024.10.043 · Cited by 9
Xu, S., Guan, Y., Wei, C., & Xu, H. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109962 · Cited by 8
Fan, W., Si, Y., Sun, M., Zhou, L., Yang, W., Alhudhaif, A., & Alenezi, F. S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126824 · Cited by 11
Incremental Semisupervised Learning With Adaptive Locality Preservation for High-Dimensional Data
Li, G., Yu, Z., Yang, K., Fan, Z., & Chen, C. L. P. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3560592 · Cited by 8
“In this section, we provide a brief overview of broad learning system (BLS) [1] and graph-based semisupervised BLS.”
InfluentialSelf-citationZheng, X., Cheng, Z., Cheng, J., Hon, C. T., & Yang, Y. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113350 · Cited by 9
Wang, Z., Tang, J., & Aljerf, L. (2025) · Chemical Engineering Science · doi:10.1016/j.ces.2025.122960 · Cited by 8
A Flexible Approach for Human Activity Recognition Based on Broad Learning System
Lin, Z., Chen, H., Yang, Q., & Hong, X. (2019) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3318299.3318318 · Cited by 8
“Efficient and effective learning capability of BLS has been demonstrated in [5] and [6].”
BackgroundMethodOnboard target detection in hyperspectral image based on deep learning with FPGA implementation
Shibi, C. S., & Gayathri, R. (2021) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2021.104313 · Cited by 8
Gu, T., Wang, D., & Li, Y. (2022) · Journal of The Electrochemical Society · doi:10.1149/1945-7111/ac8ee0 · Cited by 8
Broad Learning System for Indoor CSI Fingerprint Localization
Yu, C., Sheu, J., & Kuo, Y.-C. (2023) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc55385.2023.10119111 · Cited by 8
Ni, M., & Li, S. (2023) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2023.108324 · Cited by 8
CADM: Confusion Model-Based Detection Method for Real-Drift in Chunk Data Stream
Hu, S., Liu, Z., & He, X. Y. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-34899-0_13 · Cited by 9
Self-citationComprehensive Evaluation of Marine Ship Fires Risk Based on Fuzzy Broad Learning System
Zhang, C., Zhang, X., Liu, S., & Guo, M. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11071276 · Cited by 8
Li, F., Ge, J., Wang, X., Zhao, G., Yu, X., & Li, X. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-023-01393-6 · Cited by 9
“As a new type of deep neural network, the broad learning system (BLS) proposed in 2018 overcomes the deficiencies of DNNs [11, 12].”
Bearing Rigidity-Based Flocking Control of AUVs via Semi-Supervised Incremental Broad Learning
Cao, W., Yan, J. J., Yang, X., Chen, C., & Guan, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3406720 · Cited by 8
“Nevertheless, the solutions in [29], [30], [31], [32], [33], [34], [35], and [36] aim at the one-shot optimization, which cannot be directly applied to the flocking procedure due to continue-time approximations of states and control inputs for AUVs.”
Self-citationZhu, F., Zhang, Y., Wang, J., Luo, X., Liu, D., Jin, K., & Peng, J. (2024) · Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy · doi:10.1016/j.saa.2024.125357 · Cited by 8
Adaptive feature expansion and fusion model for precast component segmentation
Yuen, K., & Ye, G. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13523 · Cited by 8
Hard Shadows Removal Using an Approximate Illumination Invariant
Wang, B., Chen, C. L. P., Li, Y., & Zhao, Y. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461695 · Cited by 8
Self-citationEdge Computing Based Traffic Analysis System Using Broad Learning
Peng, X., Ota, K., & Dong, M. (2019) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-22971-9_20 · Cited by 8
Mixed-Norm Based Broad Learning System for EEG Classification
Zheng, Y., Qin, X., Xi, Z., & Chen, B. (2019) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2019.8856666 · Cited by 8
“where S is the soft thresholding operator [2].”
BackgroundMethodComparison and Combination of Activation Functions in Broad Learning System
Xu, L., & Chen, C. L. P. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9282871 · Cited by 9
“Complete deduction and principles could be checked in [6].”
BackgroundMethodInfluentialSelf-citationA near effective and efficient model in recognition
Li, H., Zhou, Z., Li, C., & Suen, C. Y. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108173 · Cited by 8
Pruning Broad Learning System based on Adaptive Feature Evolution
Liu, Y., Yang, K., Yu, Z., Liu, Z., Shi, Y., & Chen, C. L. P. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533681 · Cited by 9
Self-citationJin, Q., Lin, R., & Yang, F. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2021.104640 · Cited by 8
Classifying Denial of Service Attacks Using Fast Machine Learning Algorithms
Li, Z., Rios, A. L. G., & Trajković, L. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9659239 · Cited by 8
“Broad learning system [7], [8] is based on the random vector functional-link neural network.”
BackgroundMethodInfluentialResearch on Vision of Intelligent Car Based on Broad Learning System
Liu, X., & Wu, Y. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3137801 · Cited by 8
“After the feature vector of the image of the target identifier to be detected is determined, the image category and candidate box coordinates of the target identifier to be detected can be obtained according to the weight value corresponding to the trained recognition object categories [25], [30].”
MethodCPG-Inspired Gait Generation and Transition Control for Six Wheel-legged Robot
Deng, C., Wang, S., Chen, Z., Wang, J., Ma, L., & Li, J. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9727252 · Cited by 8
Target tracking method of Siamese networks based on the broad learning system
Zhang, D., Chen, C. L. P., Li, T., Zuo, Y., & Duy, N. Q. (2022) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12134 · Cited by 8
Self-citationWang, Z., Li, J., Zhang, T., & Yuan, S. (2022) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01680-x · Cited by 8
“put forward a broad learning system (BLS) [25] based on the random vector functional-link neural network (RVFLNN) [26].”
BackgroundMethodPhotovoltaic Power Prediction Based on EMD-BLS Model
Bao, Y., & Guo, W. (2023) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2427/1/012016 · Cited by 8
Quantized minimum error entropy with fiducial points for robust regression
Zheng, Y., Wang, S., & Chen, B. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.09.034 · Cited by 8
Xu, Y., Wang, H., Liu, X., & Sun's, W. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.01.030 · Cited by 9
Broad Learning for Optimal Short-Term Traffic Flow Prediction
Liu, D., Yu, W., & Baldi, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-22796-8_25 · Cited by 8
An Incremental Identification Method for Fraud Phone Calls Based on Broad Learning System
Zhong, R., Dong, X., Lin, R., & Zou, H. (2019) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct46805.2019.8947271 · Cited by 8
Performance analysis of fuzzy BLS using different cluster methods for classification
Feng, S., & Chen, C. L. P. (2020) · Science China Information Sciences · doi:10.1007/s11432-018-9630-0 · Cited by 8
Self-citationAn Accelerated Maximally Split ADMM for a Class of Generalized Ridge Regression
Lai, X., Cao, J., & Lin, Z. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3104840 · Cited by 8
“machine (ELM) [6], the broad learning system (BLS) [7], and the extreme minimal learning machine (EMLM) [8], [9]”
BackgroundMethodInfluentialHe, Y., Ye, X., Huang, J. Z., & Fournier‐Viger, P. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3495164 · Cited by 9
A Fault Aware Broad Learning System for Concurrent Network Failure Situations
Adegoke, M., Wong, H. T., & Leung, C.-S. (2021) · IEEE Access · doi:10.1109/access.2021.3066217 · Cited by 10
Multi-view daily action recognition based on Hooke balanced matrix and broad learning system
Liu, Z., Lu, B., Wu, Y., & Gao, C. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.104919 · Cited by 8
Self-citationZuo, G., Dong, S., Zhou, J., Yu, S., & Zhao, M. (2025) · Control Engineering Practice · doi:10.1016/j.conengprac.2025.106278 · Cited by 7
Federated fault diagnosis using data fusion in large-scale heterogeneous unmanned systems
Li, R., Jiang, B., Zong, Y., Lu, N., & Guo, L. (2025) · Control Engineering Practice · doi:10.1016/j.conengprac.2025.106284 · Cited by 9
MFBLS: A Mixture-of-Experts-Based Fuzzy Broad Learning System for Tackling Imbalanced Datasets
Wang, J., Nie, L., Duan, J., Zhao, H., & Chen, C. L. P. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3576155 · Cited by 7
“It extends the architecture of broad learning system (BLS) [18], wherein the feature nodes on the left side of BLS are substituted with TS fuzzy systems.”
Self-citationLitANFIS: Literal-aware Adaptive Neuro-Fuzzy Inference System to learn Conjunctive Normal Form
Parchamijalal, M. M., & Salimi-Badr, A. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130658 · Cited by 7
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.