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 701–800 of 1,000
Shen, L., Shi, J., Gong, B., Zhang, Y., Dong, Y., Zhang, Q., & An, H. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8512990 · Cited by 13
“For more details about BLS, please refer to [9].”
BackgroundMethodInfluentialA neighborhood prior constrained collaborative representation for classification
Li, Y., Jin, J., Zhao, L., Wu, H., Sun, L., & Chen, C. L. P. (2020) · International Journal of Wavelets Multiresolution and Information Processing · doi:10.1142/s0219691320500733 · Cited by 13
Self-citationFrom WASD to BLS with application to pattern classification
Liu, M., Li, H., Li, Y., Jin, L., & Huang, Z. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107455 · Cited by 12
Zhan, C., Wu, Z., Wen, Q., Gao, Y., & Zhang, H. (2021) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom49281.2021.9399020 · Cited by 13
“Finally, based on historical data and augmented data, a hybrid broad learning system (BLS) [13], in which PSO is utilized for optimizing the hyper-parameters of BLS, is proposed.”
MethodBroad Echo State Network with Reservoir Pruning for Nonstationary Time Series Prediction
Liu, W., Bai, Y., Jin, X., Wang, X., Su, T., & Kong, J. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/3672905 · Cited by 12
“BLS is different from deep learning, and the network structure is not deepened vertically but expanded horizontally and consumes more computer resources [12].”
BackgroundMethodInfluentialA broad learning-based state estimation method for power system
Luo, L., Wang, J., Zhou, S., Lou, G., & Sun, J. (2022) · Energy Reports · doi:10.1016/j.egyr.2022.02.299 · Cited by 12
A Semi-Supervised Progressive Learning Algorithm for Brain–Computer Interface
Wei, Y., Li, J., Ji, H., Jin, L., Liu, L., Bai, Z., & Ye, C. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3192448 · Cited by 13
Incremental Multilayer Broad Learning System With Stochastic Configuration Algorithm for Regression
Ding, S., Zhang, C., Zhang, J., Guo, L., & Ding, L. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3192536 · Cited by 12
“and efficient randomized neural network model [6]–[8].”
BackgroundMethodInfluentialDoğan, G., & Ergen, B. (2022) · Iran Journal of Computer Science · doi:10.1007/s42044-022-00125-6 · Cited by 12
“[39] by inheriting most of the features and superiorities of the random vector functional-link neural networks (RVFLNN).”
Detecting Cloud Anomaly via Broad Network-Based Contrastive Autoencoder
Zhong, G., Liu, F., Jiang, J., Wang, B., Yao, X., & Chen, C. L. P. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3353772 · Cited by 15
“The broad network [45] is an improved single-layer feed-forward neuron model.”
BackgroundSelf-citationBoosted unsupervised feature selection for tumor gene expression profiles
Shi, Y., Yang, K., Wang, M., Yu, Z., Zeng, H., & Hu, Y. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12317 · Cited by 12
Probability Density Rank-Based Quantization for Convex Universal Learning Machines
Qin, Z., Chen, B., Gu, Y., Zheng, N., & Príncipe, J. C. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2935502 · Cited by 12
“One produces the data-centered functional bases [1], [2] and the other randomly generates the nonlinear projection mappings [3], [6].”
BackgroundTsai, C., Hsu, C., Wu, C.-W., & Tai, F. (2019) · International Journal of Fuzzy Systems · doi:10.1007/s40815-019-00739-2 · Cited by 12
Prediction of Ship Fuel Consumption Based on Broad Learning System
Li, X., Zhu, Y., Zuo, Y., Li, T., & Chen, C. L. P. (2019) · International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) · doi:10.1109/spac49953.2019.237871 · Cited by 12
“The Figure 4 shows the network architecture of BLS [6][10].”
BackgroundMethodSelf-citationFault Diagnosis Method of Power Electronic Converter Based on Broad Learning
Han, R., Wang, R., & Zeng, G. (2020) · Complexity · doi:10.1155/2020/7463291 · Cited by 12
“Recently, Chen and Liu developed a very fast and effective broad learning system (BLS) [23].”
BackgroundLiao, Z., Huang, J., Cheng, Y., Li, C., & Liu, P. X. (2022) · Applied Intelligence · doi:10.1007/s10489-021-02864-8 · Cited by 12
“Wei , Whk , ei , and hk are randomly generated weight matrices and bias matrices, which are fine-tuned by a sparse encoder [18].”
BackgroundBroad-learning recurrent Hermite neural control for unknown nonlinear systems
Hsu, C., Chen, B.-R., & Wu, B. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108263 · Cited by 12
Deep compression of probabilistic graphical networks
Zhang, C.-Y., Zhao, Q., Chen, C. L. P., & Liu, W. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.106979 · Cited by 12
Self-citationA Stochastic Attention CNN Model for Rumor Stance Classification
Bai, N., Wang, Z., & Meng, F. (2020) · IEEE Access · doi:10.1109/access.2020.2990770 · Cited by 13
“According to the theory of Extreme Learning Machines (ELMs) and Broad Learning Systems (BLSs), the classification model will be convergent when the number of stochastic hidden units is large enough [34], [35].”
MethodMao, Y., Dang, P., Zhang, E., Tang, C., Chen, Y., & Chen, X. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108619 · Cited by 11
Generalized sparse radial basis function networks for multi-classification problems
Dai, Y., Wu, Q., & Zhang, Y. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111361 · Cited by 11
Boosting Adaptive Weighted Broad Learning System for Multi-Label Learning
Lin, Y., Yu, Z., Yang, K., Fan, Z., & Chen, C. L. P. (2024) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2024.124557 · Cited by 11
Self-citationBroad Distributed Game Learning for intelligent classification in rolling bearing fault diagnosis
Liu, H., Pan, H., Zheng, J., Tong, J., & Zhu, M. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112470 · Cited by 11
Adaptive weights-based relaxed broad learning system for imbalanced classification
Li, Y., Gao, Y., Jin, J., Nan, J., Meng, Y., Wang, M., & Chen, C. L. P. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104869 · Cited by 11
Self-citationZhang, Y., Liu, Y., Wang, J., Xuan, Q., Lin, Y., & Gui, G. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3524157 · Cited by 11
Persistent Excitation of Improved RBF Neural Networks: Neuron Dynamic-Growing Strategy
Wang, M., Wang, M., & Yang, C. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3528118 · Cited by 11
“This brief proposes an improved RBF NN with a novel neuron dynamic-growing (NDG) strategy by means of the broad learning framework (see [32], [33]).”
Learning Through Deterministic Assignment of Hidden Parameters
Fang, J., Lin, S.-B., & Xu, Z. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2885029 · Cited by 11
“As the popularity of neural networks in recent years [6], [9], [35], [48], we equip the LtDaHP scheme with an FNN-instance to show its outperformance.”
MethodLi, J., Zhong, J., Yang, J., & Yang, C. (2020) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2020.00055 · Cited by 11
“Considering these problems of deep structure learning methods, Chen and Liu (2017) proposed an incremental learning method, which provides an alternative way for deep structure neural network (Liu and Chen, 2017).”
MethodRen, C., Xu, Y. H., Zhao, J., Zhang, R., & Wan, T. (2021) · CSEE Journal of Power and Energy Systems · doi:10.17775/cseejpes.2020.05930 · Cited by 11
Huang, J., Li, C., Huang, Z., & Liu, P. X. (2021) · Electrical Engineering · doi:10.1007/s00202-021-01389-0 · Cited by 11
“The other is machine learning methods such as long short-term memory (LSTM) network [10], RVFL [11], DBN [12], BLS [13], SVR [14, 15], and RFR [16].”
MethodInfluentialA new machine learning model based on the broad learning system and wavelets
Jara-Maldonado, M., Alarcon‐Aquino, V., & Rosas-Romero, R. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.104886 · Cited by 11
Graph-Represented Broad Learning System for Landslide Susceptibility Mapping in Alpine-Canyon Region
Xu, L., Chen, C. L. P., Qing, F., Meng, X., Zhao, Y. N., Qi, T., & Miao, T. (2022) · Remote Sensing · doi:10.3390/rs14122773 · Cited by 13
Self-citationAn incremental cross-modal transfer learning method for gesture interaction
Zhong, J., Li, J., Lotfi, A., Liang, P., & Yang, C. (2022) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2022.104181 · Cited by 11
Variational expectation maximization attention broad learning systems
Hu, X., Wei, X., Gao, Y., Liu, H., & Zhu, L. (2022) · Information Sciences · doi:10.1016/j.ins.2022.06.074 · Cited by 11
Su, L., Yang, J., Li, F., & Jiang, Y. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103748 · Cited by 11
Wang, D., & Yang, S. X. (2022) · Intelligence & Robotics · doi:10.20517/ir.2022.25 · Cited by 11
“The broad learning system (BLS) method([64,65]) is a kind of neural network that does not depend on the structure depth and can realize the diagnosis of research problems by widening the width of the network for information mining.”
MethodLiu, Z., Leung, C.-S., & So, H. C. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.02.012 · Cited by 13
Self-citationHuang, Y., Huang, Y., Shuncong Zhong, A., Zhuang, C., Shi, T., Zhang, Z., Chen, Z., & Liu, X. (2023) · Coatings · doi:10.3390/coatings13030513 · Cited by 11
Zhu, C., Yang, H., Jin, X., Xu, K., & Shen, W. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3257311 · Cited by 13
Lu, J., Cui, R., & Li, S. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acca37 · Cited by 11
“To solve the above problems, broad learning system (BLS)is proposed by Junlong Chen et al [20].”
BackgroundDeepBLS: Deep Feature-Based Broad Learning System for Tissue Phenotyping in Colorectal Cancer WSIs
Bakht, A. B., Javed, S., Gilani, S. Q., Karki, H., Muneeb, M., & Werghi, N. (2023) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-023-00797-x · Cited by 12
“While the BLS architecture described above shows actually five sets of trainable parameters, namely, Wf , f , Wh , h , and W, we opted for the original configuration reported in [27] where Wf , f , Wh , h are generated randomly.”
BackgroundMethodInfluentialWang, X., Guo, X., Xu, S., & Zhao, X. (2024) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2023.109764 · Cited by 11
Remaining Life Prediction of Li-Ion Batteries Considering Sufficiency of Historical Data
Xin, Z., Zhang, X., Gong, Q., Ma, F., & Wang, Y. (2024) · Journal of The Electrochemical Society · doi:10.1149/1945-7111/ad24c1 · Cited by 11
Ship order book forecasting by an ensemble deep parsimonious random vector functional link network
Cheng, R., Gao, R., & Yuen, K. F. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108139 · Cited by 11
Student body gesture recognition based on Fisher broad learning system
Shi, Y., Wei, Y., Pan, D., Deng, W., Yao, H., Chen, T., Zhao, G. L., Tong, M., & Liu, Q. (2018) · International Journal of Wavelets Multiresolution and Information Processing · doi:10.1142/s0219691319500012 · Cited by 11
Tan, F., & Guan, X. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2876455 · Cited by 12
“Compared with the classical adaptive filtering algorithms, the kernel adaptive algorithms have the following advantages [62], [66]–[69]: 1) effective processing of nonlinear signals; 2) better generalization learning ability; 3) simple structure and convenient calculation; 4) significantly reduc-”
BackgroundMethodEstimating Cement Compressive Strength from Microstructure Images Using Broad Learning System
Dang, Y., Wang, L., Yin, J., Zhu, X., Feng, Z., & Guo, J. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00716 · Cited by 11
“In Table I, the type of input of CNN and the second BLS is voxel matrix of original microstructure image, and other methods take feature matrix extracted from images as input.”
BackgroundInfluentialDecoding EEG in Motor Imagery Tasks with Graph Semi-Supervised Broad Learning
She, Q., Zhou, Y., Gan, H., Ma, Y., & Luo, Z. (2019) · Electronics · doi:10.3390/electronics8111273 · Cited by 13
Liu, Z., Chen, C. L. P., Zhang, T., & Zhou, J. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914328 · Cited by 11
“Recently, an efficient and effective discriminative learning algorithm named “Broad Learning System” (BLS) and its variants are proposed in [21], [22].”
BackgroundMethodSelf-citationConstruction of Multi-State Transient Stability Boundary Based on Broad Learning
Tian, Y., Wang, K., Oluic, M., Ghandhari, M., Xu, J. Q., & Li, G. (2020) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2020.3047611 · Cited by 15
“Recently, an effective and efficient broad learning system (BLS) has been developed [13].”
BackgroundMethodZhang, M., Wu, L., & Peng, Z. (2021) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea51954.2021.9516254 · Cited by 13
Industrial Process Monitoring Based on Dynamic Overcomplete Broad Learning Network
Peng, C., Xu, Y., & ZhiQi, H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3185167 · Cited by 11
“In order to adapt to the demand for self-updating capability of models preferably, Chang et al. [22] based on copious literature extended the broad learning system (BLS) model proposed by Chen and Liu [23] to the domain of batch process.”
MethodJia, J., Wu, G., & Qiu, W. (2022) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2022.894874 · Cited by 12
“In the next work, we are going to apply deep learning to extract features and then use multiple BLS to build stacking ensemble classi fi er for the prediction of succinylation sites, which we believe will have more unexpected gains in the next experiments.”
MethodInfluentialRospawan, A., Tsai, C., & Tai, F. (2022) · International Conference on System Science and Engineering · doi:10.1109/icsse55923.2022.9948234 · Cited by 11
“Recently, the authors in [10] and [11] presented a broad learning system (BLS) to construct a fast and efficient neural network, and the authors in [12]–[16] proposed a method that incorporated Takagi-Sugeno fuzzy system inside the BLS by adding the enhancement node to enhance learning capabilities.”
MethodTian-hao, L., Sun, F., Sun, R., Wang, L., Li, M., & Yang, H. (2018) · International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) · doi:10.1109/spac46244.2018.8965566 · Cited by 11
“Chen and Liu [10] proposed broad learning system to improve conventional neural network and accelerate training process.”
BackgroundMa, W., Tang, J., Aljerf, L., Liang, Y., & Maad, A. H. (2025) · Sustainability · doi:10.3390/su172210097 · Cited by 10
Feng, Q., Chen, C. L. P., & Liu, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3276393 · Cited by 12
“The first way is to leverage representation learning techniques [29], [30], [31], [32], [33], [34], [35], [36] for clustering, such as kernel-based clustering [37], [38], [39], [40], [41], matrix factorization-based clustering [42], [43], [44], adaptive graph-based clustering [45], [46], spectral…”
MethodSelf-citationSun, S., Xu, H., Li, Y., Li, P., Sheng, B., & Lin, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3288134 · Cited by 10
“T-SNE [46] embedding of selected samples in different AL rounds (b-d) and full dataset (a), the former feature is extracted from the output of the model learned by the AL models, and the latter is from Broad Learning System (BLS) [22].”
BackgroundMethodInfluentialSalimi-Badr, A. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111458 · Cited by 10
Gu, Z., Shen, Y., Wang, Z., Qiu, J., Li, W., Huang, C., Jiang, Y., & Li, P. (2024) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2024.108180 · Cited by 8
Gu, Z., Shen, Y., Wang, Z., Jiang, Y., Chun, H., & Li, P. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3384597 · Cited by 11
Double Broad Q-Network for Overtaking Control of Autonomous Driving
Peng, X., Bu, X., Zhang, X., Dong, M., & Ota, K. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3390571 · Cited by 11
A Strong UAV Vision Tracker Based on Deep Broad Learning System and Correlation Filter
Wang, M., Ge, Q., Zhu, B., & Sun, C. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3429161 · Cited by 10
“Here, F B † is the pseudoinverse of F B , details can be found in [21].”
InfluentialMiao, J., Liu, X., Guo, L., & Chen, L. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112343 · Cited by 10
Tian, H., Tang, J., & Wang, T. (2024) · Sustainability · doi:10.3390/su16177670 · Cited by 10
“To address this, Chen et al. [29] designed a broad learning system (BLS) based on the random vector functional link neural network, training parameters using a ridge regression pseudo-inverse algorithm [30].”
Li, W., Liu, Z., Han, P., He, X. H., Wang, L., & Zhang, T. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130137 · Cited by 10
Self-citationJiang, K., Niu, B., Li, J., Duan, P., Wang, J., & Yang, D. (2018) · IEEE Access · doi:10.1109/access.2018.2877798 · Cited by 10
Depth-based human activity recognition via multi-level fused features and fast broad learning system
Yao, H., Yang, M., Chen, T., Wei, Y., & Zhang, Y. (2020) · International Journal of Distributed Sensor Networks · doi:10.1177/1550147720907830 · Cited by 10
“Broad learning system (BLS) 30 is proposed as an improvement of the random vector functional link neural network (RVFLNN).”
BackgroundMethodHuang, J., Zhou, Z., Li, C., Liao, Z., & Liu, P. X. (2021) · IET Generation Transmission & Distribution · doi:10.1049/gtd2.12265 · Cited by 11
Damage Detection in Wind Turbine Blades Based on an Improved Broad Learning System Model
Zou, L., Wang, Y., Bi, J., & Sun, Y. (2022) · Applied Sciences · doi:10.3390/app12105164 · Cited by 10
“The BLS was proposed by Philip Chen in 2017 [13,14].”
MethodBack-propagation extreme learning machine
Zou, W., Xia, Y., & Cao, W. (2022) · Soft Computing · doi:10.1007/s00500-022-07331-1 · Cited by 10
Broad learning system based on driving amount and optimization solution
Zou, W., Xia, Y., & Cao, W. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105353 · Cited by 10
Wind power forecast based on broad learning system and simplified long short term memory network
Han, L., Li, M., Wang, X., & Lu, P. (2022) · IET Renewable Power Generation · doi:10.1049/rpg2.12588 · Cited by 11
Broad Minimax Probability Learning System and its Application in Regression Modeling
Chu, F., Liang, T., Chen, C. L. P., Ma, X., & Wang, X. (2022) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2022.3211519 · Cited by 11
“With the perfect balance between prediction accuracy and learning efficiency, broad learning system (BLS) [4] and its variations [5] have attracted more and more attention from the academia and industrial community [6], [7].”
BackgroundSelf-citationBroad Learning System-Based Detector for OFDM With Index Modulation
Du, R., Wang, S., & Liu, F. (2022) · IEEE Communications Letters · doi:10.1109/lcomm.2022.3216304 · Cited by 10
“BLS is built as a flat network in which the raw signal bits are transmitted and placed as “mapped feature” in feature nodes and the structure is extended in the “enhancement nodes” [15], [16].”
Flood Forecasting Method Based on Improved VMD-FOS-QR-RBL
Liu, Y., Wang, L., Du, S., Li, Z., & Liu, X. (2022) · IEEE Access · doi:10.1109/access.2022.3232405 · Cited by 10
FBL-ET: A federated broad learning framework based on event trigger
Ren, C., An, R., & Xuan, Z. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110366 · Cited by 10
Optimizing job scheduling by using broad learning to predict execution times on HPC clusters
Hou, Z., Shen, H., Feng, Q., Lv, Z., Jin, J., Zhou, X., & Gu, J. (2023) · CCF Transactions on High Performance Computing · doi:10.1007/s42514-023-00137-z · Cited by 10
Randomization-based neural networks for image-based wind turbine fault diagnosis
Wang, J., Yang, Y., & Li, N. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106028 · Cited by 10
Shen, K., Zhuang, Y., Chen, Y., Zuo, S., & Liu, T. (2023) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.05.008 · Cited by 13
Wang, N., Jia, L., Qin, Y., Li, Z., Miao, B., Geng, J., & Wang, Z. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110653 · Cited by 10
Impact of ChatGPT in Higher Education Learning
Jemmy, J., Aina, M., Wahdah, W., Joshua, W., & Sabri, S. (2023) · Journal International of Lingua and Technology · doi:10.55849/jiltech.v3i1.505 · Cited by 14
“As time goes by, technological developments are increasingly advanced so that technology becomes one of the facilities that must exist in the teaching and learning process (C. L. P. Chen & Liu, 2018).”
BackgroundWu, L., Zhang, C., Qin, F., Fei, H., Liu, G., Zhang, J., & Xu, S. (2024) · Processes · doi:10.3390/pr12020369 · Cited by 10
“In 2018, C. L. Philip Chen introduced a Flattened Broad Learning System (BLS) [18].”
Bakhshi, S., & Can, F. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111489 · Cited by 11
Fast Sensitivity-Analysis-Based Online Self-Organizing Broad Learning System
Yi, L., Ding, J., Liu, C., & Chai, T. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3361017 · Cited by 12
“The proposed SASO-BLS is compared with four random weight feed-forward neural networks (RVFL [6], CRVFL [25], SCN [7], BLS [8], BCNN [10]) and two accepted online learning methods (LSTM [3] and GRU [26]).”
BackgroundMethodSelf-balancing Incremental Broad Learning System with privacy protection
Zhang, W., Liu, Z., Jiang, Y., Chen, W., Zhao, B., & Yang, K. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106436 · Cited by 11
Self-citationClustering Based on Supervised Learning of Exemplar Discriminative Information
Duan, L., Cui, S., Qiao, Y., & Yuan, B. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2870549 · Cited by 10
“Some supervised learning approaches could achieve high performance with high efficiency, for example broad learning system (BLS) [9], [10].”
BackgroundMethodEvolving Generalized Modulatory Learning: Unifying Neuromodulation and Synaptic Plasticity
Wang, L., Zheng, J., & Orchard, J. (2019) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2019.2960766 · Cited by 10
“Another noniterative example is the broad learning system (BLS) [17], [18], in which the structure can be expanded in an incremental way without having to start the retraining from scratch.”
Foreign body recognition for coal mine conveyor based on improved PCANSet
Zhao, X., Li, X., Yin, L., Feng, W., Zhang, N., & Zhang, X. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8927930 · Cited by 10
“The method has been achieved better performance in many image classification tasks [14-18], and become a research hotspot in the field of image recognition.”
MethodBroad Learning System for Nonparametric Modeling of Clay Parameters
Kuok, S., & Yuen, K. (2020) · ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part A Civil Engineering · doi:10.1061/ajrua6.0001066 · Cited by 10
Zhu, H., Liu, Z., Chen, C. L. P., & Liang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3052102 · Cited by 11
“Firstly, the input data X is projected by to become the i -th group of mapped features Z i , where the weights W e i and the biases β e i are randomly generated and then fine-tuned by applying the linear inverse problem [19].”
BackgroundMethodInfluentialSelf-citationLi, J., Hua, C., & Yang, Y. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3063200 · Cited by 10
“RVFLNs [22], [30] is a special SLFN, in which the input weights and biases are selected randomly, then the output weights can be obtained by Moore–Penrose pseudo-inverse.”
MethodZhang, Y., Ning, X., Wang, Z. X., & Yu, D. (2021) · IEEE Access · doi:10.1109/access.2021.3083567 · Cited by 10
“In recent decades, there has been a tremendous interest in SUS, and many significant technological achievements have emerged within the aera of its control design [4]–[7].”
BackgroundMulti-Feature Broad Learning System for Image Classification
Liu, R., Liu, Y., Zhao, Y., Chen, X., Cui, S., Wang, F., & Yi, L. (2021) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001421500336 · Cited by 11
Tan, X., Xi, H.-L., Yang, J., & Wang, W. (2021) · Computational and Mathematical Methods in Medicine · doi:10.1155/2021/7822119 · Cited by 10
“As a novel neural network model based on random vector functional-link neural network (RVFLNN), BLS is suitable for processing relatively simple data and has a faster learning speed [15].”
MethodAntenna Optimization Based on Auto-Context Broad Learning System
Ding, W., Meng, F., Tian, Y., & Yuan, H. (2022) · International Journal of Antennas and Propagation · doi:10.1155/2022/7338164 · Cited by 10
“Broad learning system (BLS) [15] is proposed to solve the problem of plenty of time and computing resources that the above-mentioned deep structure suffers due to the need to adjust large numbers of parameters and its complicated manual design structure.”
Improved BLS based transformer fault diagnosis considering imbalanced samples
Xu, C., Li, X., Wang, Z., Zhao, B., & Xie, J. (2022) · Energy Reports · doi:10.1016/j.egyr.2022.02.223 · Cited by 10
Self-Organizing Multichannel Deep Learning System for River Turbidity Monitoring
Gu, K., Liu, J., Shi, S., Xie, S., Shi, T., & Qiao, J. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3205915 · Cited by 17
“The sec-508 ond group of four state-of-the-art learning systems is com-509 posed of bidirectional ELM (BELM) [73], stacked selective ensemble-backed predictor (SSEP) [6], broad learning system (BLS) [74], and RFE-GEE [44].”
Intelligent and Smart Cloud Based Autonomous Robotic Kitchen System
Sharath, B., Srisha, R., Shashidhar, K. V., & Bharadwaj, S. S. (2018) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iccons.2018.8663208 · Cited by 10
“There are many methods proposed [3], [4] for this application.”
MethodOnline ADMM-Based Extreme Learning Machine for Sparse Supervised Learning
Song, T., Li, D., Liu, Z., & Yang, W. (2019) · IEEE Access · doi:10.1109/access.2019.2915970 · Cited by 10
“Based on the above ideas of 1) random parameters and 2) least squares solution of β, some improved ELMs are proposed to overcome the problems from different aspects in practice, such as incremental ELM [43] to enhance online update capability, multi-layer ELM [27] for highdimensional input problem, dual-ELM network [2…”
BackgroundSelf-citation
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.