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 101–200 of 1,000
Peng, G., Cheng, Y., Zhang, Y., Shao, J., Wang, H., & Shen, W. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.08.014 · Cited by 88
Xu, X., Bao, S., Shao, H., & Shi, P. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102419 · Cited by 90
Xu, X., Hu, S., Shi, P., Shao, H., Li, R., & Li, Z. (2022) · Energy · doi:10.1016/j.energy.2022.125342 · Cited by 83
Chen, K., Zhu, X., Anduv, B., Jin, X., & Du, Z. (2022) · Energy · doi:10.1016/j.energy.2022.124040 · Cited by 84
Neuro-Fuzzy Random Vector Functional Link Neural Network for Classification and Regression Problems
Sajid, M., Malik, A. K., Tanveer, M., & Suganthan, P. N. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3359652 · Cited by 95
“8) BLS: Standard broad learning system [37].”
Residual GCB-Net: Residual Graph Convolutional Broad Network on Emotion Recognition
Li, Q., Zhang, T., Chen, C. L. P., Yi, K., & Chen, L. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3147839 · Cited by 85
“By integrating the advantages of DGCNN and broad learning system (BLS) [46]–[48], Wang et al. proposed the broad dynamical graph learning system (BDGLS) [49] to extract features on non-Euclidean domain and randomly generating nodes to find the desired connection weights simultaneously.”
BackgroundSelf-citationMachine Learning Techniques for Classifying Network Anomalies and Intrusions
Li, Z., Rios, A. L. G., Xu, G., & Trajković, L. (2019) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2019.8702583 · Cited by 82
“(SVM) [13], Long Short-Term Memory (LSTM) [8], [22], [25], [34], and Gated Recurrent Unit (GRU) [18], [42] as well as recently proposed Broad Learning System (BLS) [16], [17], [33].”
BackgroundMethodInfluentialPeng, G., Chen, C. L. P., & Yang, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3057958 · Cited by 78
“Recently, the broad learning system (BLS) has been widely studied [39]–[41].”
BackgroundSelf-citationFuzzy Tracking Control for a Class of Uncertain MIMO Nonlinear Systems With State Constraints
He, W., Kong, L., Dong, Y., Yu, Y., Yang, C., & Sun, C. (2017) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2749124 · Cited by 77
“In recent years, to obtain the accurate control of MIMO systems such that considered systems can track reference trajectories, many researches have tried fuzzy control [4]–[14], neural network (NN) control [15]–[19], adaptive control [20]–[36], machine learning control [37]–[39], nonlinear model predictive control [40…”
BackgroundLiu, J., Niu, B., Kao, Y., Zhao, P., & Yang, D. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3015847 · Cited by 77
Gong, X., Chen, C. L. P., & Zhang, T. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3298324 · Cited by 89
“Recently, the broad learning system (BLS) [13], [14], [15], an effective discriminative learning algorithm, has emerged as a fast and lightweight option for deep neural networks.”
BackgroundSelf-citationCorrNet: Fine-Grained Emotion Recognition for Video Watching Using Wearable Physiological Sensors
Zhang, T., Ali, A. E., Wang, C., Hanjalić, A., & Cesar, P. S. (2020) · Sensors · doi:10.3390/s21010052 · Cited by 89
“Then, the first feature node A 1 can be calculated by: where Although this method is fast, the nature of randomness suffers from unpredictability [84].”
BackgroundMethodInfluentialStacked one-class broad learning system for intrusion detection in industry 4.0
Yang, K., Shi, Y., Yu, Z., Yang, Q., Sangaiah, A. K., & Zeng, H. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3157727 · Cited by 75
“In order to address the above problems, the state-of-the-art broad learning system (BLS) [17] provides an alternative way of network training.”
BackgroundHeterogeneous Multilayer Generalized Operational Perceptron
Tran, D. T., Serkan Kiranyaz, B., Gabbouj, M., & Iosifidis, A. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2914082 · Cited by 76
“4) Broad Learning System (BLS) [25]: Based on the idea of random vector functional link neural network [44], the authors proposed a progressive learning algorithm that increments the width of a two-hidden-layer network.”
BackgroundAn RUL prediction approach for lithium-ion battery based on SADE-MESN
Ji, Y., Chen, Z., Shen, Y., Yang, K., Wang, Y., & Cui, J. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107195 · Cited by 74
Flexible Label-Induced Manifold Broad Learning System for Multiclass Recognition
Jin, J., Geng, B., Li, Y., Liang, J., Xiao, Y., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3291793 · Cited by 73
“We select some state-of-the-art algorithms as competitors, including ELM [24], SRC [1], CRC [25], SVM [26], DLSR [15], GBLS [27], ReLSR [16], IDLSR [28], RLR [29], standard BLS [7], SGLDBLS [30], DRAGD [31], Fisher [32], DRC [33], and MDBLS [34].”
BackgroundMethodSelf-citationYuan, B., Mingze, Z. H. A. O., Meng, S., Zhang, W., & ZHENG, H. (2023) · Petroleum Exploration and Development · doi:10.1016/s1876-3804(24)60482-9 · Cited by 73
Classification of EEG Signals on VEP-Based BCI Systems With Broad Learning
Gao, Z., Dang, W., Liu, M., Guo, W., Ma, K., & Chen, G. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2964684 · Cited by 75
Data Scarcity in Recommendation Systems: A Survey
Chen, Z., Gan, W., Wu, J., Hu, K., & Lin, H. (2024) · ACM Transactions on Recommender Systems · doi:10.1145/3639063 · Cited by 120
“Data scarcity is a prevalent issue encountered by recommendation systems (RSs) in diverse real-world situations, which hinders the ability of the RS to obtain sufficient and diverse user behavior data and item information.”
An Improved Result on Sampled-Data Synchronization of Markov Jump Delayed Neural Networks
Shen, H., Jiao, S., Cao, J., & Huang, T. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2931533 · Cited by 71
BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture
Ding, Z., Chen, Y.-R., Li, N., Zhao, D., Sun, Z.-Q., & Chen, C. L. P. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3067028 · Cited by 65
“In [27], the mechanism of BLS was introduced as follows.”
BackgroundMethodSelf-citationLiu, S., Wang, X., Jiang, M., Jiang, M., Gu, Z., Li, B., & Zhang, Y. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112599 · Cited by 79
Xu, Z., Han, G., Liu, L., Zhu, H., & Peng, J. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3206309 · Cited by 73
“According to [32], the novel solution of the pseudoinverse of Am+1 can be computed using A as”
BackgroundMethodYang, P., Yang, H. D., Meng, X., Song, C. R., He, T., Cai, J., Xie, Y. Y., & Xu, K. (2023) · Journal of Energy Storage · doi:10.1016/j.est.2023.109741 · Cited by 76
Semi-Supervised Concept Learning by Concept-Cognitive Learning and Concept Space
Mi, Y., Liu, W., Shi, Y., & Li, J. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3010918 · Cited by 68
Extracting and Composing Robust Features With Broad Learning System
Yang, K., Liu, Y., Yu, Z., & Chen, C. L. P. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3137792 · Cited by 73
Self-citationNeural-Learning-Based Force Sensorless Admittance Control for Robots With Input Deadzone
Peng, G., Chen, C. L. P., He, W., & Yang, C. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2991929 · Cited by 67
“Recently, the broad learning system (BLS) has attracted much attention because of its novel framework without suffering timeconsuming training process caused by traditional deep structure, and it has been used in pattern recognition and classification [30], [31].”
BackgroundSelf-citationGlobally and Locally Semantic Colorization via Exemplar-Based Broad-GAN
Li, H., Sheng, B., Li, P., Ali, R., & Chen, C. L. P. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3117061 · Cited by 67
“(18); 3: extract the feature maps ˆ Z F and ˆ T F of the colorized image and the ground truth image, respectively, through BLS; 4: using Eq.”
MethodInfluentialSelf-citationEnsemble Deep Random Vector Functional Link Neural Network for Regression
Hu, M., Chion, J. H., Suganthan, P. N., & Katuwal, R. (2022) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2022.3213628 · Cited by 68
“RVFL’s output layer connects both the raw input features and the hidden neurons, whereas BLS first maps the input data to the so-called feature layer which is comparable to a hidden layer.”
BackgroundInfluentialDeep diagnostics and prognostics: An integrated hierarchical learning framework in PHM applications
Lin, Y., Li, X., & Hu, Y. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.01.036 · Cited by 68
Fixed-Point Minimum Error Entropy With Fiducial Points
Xie, Y., Li, Y., Gu, Y., Cao, J., & Chen, B. (2020) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2020.3001404 · Cited by 67
“…structure of the LIP model, which includes many linear and nonlinear models as special cases, such as the simple linear model, autoregressive (AR) model [18], Volterramodel [19], functional link networks [20], extreme learning machines (ELM) [21], broad learning systems (BLS) [22], and so on.”
BackgroundBai, K., Zhu, X., Wen, S., Zhang, R., & Zhang, W. (2021) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2021.3112222 · Cited by 67
Zhou, N., Xu, X., Yan, Z., & Shahidehpour, M. (2022) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2022.3174012 · Cited by 66
“where the weighting matrix WFi and bias term βFi of feature nodes are randomly generated; the mapping function φ is established using the sparse autoencoder [22].”
MethodHe, X., Chen, Q., Tang, L., Wang, W., Liu, T., Li, L., Liu, Q., & Luo, J. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3282648 · Cited by 77
“Chen and Liu [18] designed three incremental learning algorithms for BLS without retraining the entire model, including augmented node increments, feature node increments, and increments of input data.”
MethodGusa: Graph-Based Unsupervised Subdomain Adaptation for Cross-Subject EEG Emotion Recognition
Li, X., Chen, C. L. P., Chen, B., & Zhang, T. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3349770 · Cited by 78
“In addition, before the final decision layer, broad learning [30] was used to obtain an enhanced feature by integrating multi-level features.”
MethodSelf-citationModel-free data reconstruction of structural response and excitation via sequential broad learning
Kuok, S., & Yuen, K. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2020.106738 · Cited by 67
Regularized discriminative broad learning system for image classification
Jin, J., Qin, Z., Yu, D., Li, Y., Liang, J., & Chen, C. L. P. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109306 · Cited by 64
Self-citationGong, X., Chen, C. L. P., Hu, B., & Zhang, T. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3392791 · Cited by 73
Self-citationChen, C. L. P., & Wang, B. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3011937 · Cited by 65
Self-citationMultiscale Drift Detection Test to Enable Fast Learning in Nonstationary Environments
Wang, X., Kang, Q., Zhou, M., Pan, L., & Abusorrah, A. M. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2989213 · Cited by 61
“Ensemble-based methods and online adapting classifiers are two major options when building a passive algo-rithm [21]–[23].”
MethodMachine Learning for Detecting Anomalies and Intrusions in Communication Networks
Li, Z., Rios, A. L. G., & Trajković, L. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3078497 · Cited by 62
“BLS [12] and its extensions [13], [25]–[29] are alternatives to deep learning networks.”
BackgroundInfluentialFu, Y., Cao, H., Chen, X., & Ding, J. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.109353 · Cited by 61
Liu, B., Guo, J., Chen, C. L. P., Wu, X., & Zhang, T. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3288885 · Cited by 71
“In addition, the features from all blocks of GCB-Net can be also input into the BLS [36].”
BackgroundMethodSelf-citationData-Driven Detection of Hot Spots in Photovoltaic Energy Systems
Chen, H., Yi, H., Jiang, B., Zhang, K., & Chen, Z. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2896922 · Cited by 60
“However, it is a fact that the accuracy of such intelligent detection methods depend on the completeness of training samples [15], [21], [22], i.”
BackgroundDeep Neural Network for Predicting Ore Production by Truck-Haulage Systems in Open-Pit Mines
Baek, J., & Choi, Y. (2020) · Applied Sciences · doi:10.3390/app10051657 · Cited by 74
Outdoor Shadow Estimating Using Multiclass Geometric Decomposition Based on BLS
Chen, Z., Gao, T., Sheng, B., Li, P., & Chen, C. L. P. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2875983 · Cited by 60
“To avoid the unbearable training time of deep learning, we adopt the broad learning system (BLS) in our approach, which is established as a flat network [31].”
BackgroundMethodInfluentialSelf-citationLin, J., Han, G., Pan, X., Liu, Z., Chen, H., Li, D., Jia, X., Shi, Z., Wang, Z., Cui, Y., et al. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3161787 · Cited by 66
Self-citationGPU-Free Specific Emitter Identification Using Signal Feature Embedded Broad Learning
Zhang, Y., Peng, Y., Sun, J., Gui, G., Lin, Y., & Mao, S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3257479 · Cited by 58
“Hence, this article proposes to leverage the novel broad learning system (BLS) proposed in [21], [22], [23], and [24].”
BackgroundAn Interpretable Dynamic Inference System Based on Fuzzy Broad Learning
Zhao, H., Wu, Y., & Deng, W. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3316213 · Cited by 59
Peng, X., Song, S., Zhang, X., Dong, M., & Ota, K. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3360110 · Cited by 63
“The broad learning system (BLS) is a lightweight neural network architecture that improves upon the random vector functional link neural network (RVFLNN) [22].”
BackgroundA data-driven approach for designing STATCOM additional damping controller for wind farms
Zhang, G., Hu, W., Cao, D., Yi, J., Huang, Q. P., Liu, Z., Chen, Z., & Blaabjerg, F. (2019) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2019.105620 · Cited by 58
Self-citationEnhanced Fault Diagnosis Using Broad Learning for Traction Systems in High-Speed Trains
Cheng, C., Wang, W., Chen, H., Zhang, B., Shao, J., & Teng, W. (2020) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2020.3043741 · Cited by 59
“where the weighted matrix W k can be calculated via the ridge regression approximation [34] such that W k = [Zk|Hk,j ]†Y ∈ R(6+qm)×K .”
MethodType-2 Fuzzy Broad Learning System
Han, H., Liu, Z., Liu, H., Qiao, J., & Chen, C. L. P. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3070578 · Cited by 57
“To evaluate the performance of T2F-BLS, the results of T2F-BLS are compared with other methods: BLS [1], FBLS [16], RR-BLS [9], RM-BLS [11], WT1FNN [15], and IT2FNN [22].”
MethodSelf-citationAdaptive relevant vector machine based RUL prediction under uncertain conditions
Wang, X., Jiang, B., & Lu, N. (2018) · ISA Transactions · doi:10.1016/j.isatra.2018.11.024 · Cited by 57
Automatic Leader-Follower Persistent Formation Control for Autonomous Surface Vehicles
Chen, C. L. P., Yu, D., & Liu, L. (2018) · IEEE Access · doi:10.1109/access.2018.2886202 · Cited by 56
“We denote the output of the kth feature node in the ith mapping group as [25]”
BackgroundMethodSelf-citationZhu, R., Wu, S., Li, L., Lv, P., & Xu, M. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3167029 · Cited by 59
“The BLS is first proposed by Chen and Liu [11], which aims”
BackgroundMethodInfluentialLiu, Z., Zhang, J., He, X. Y., Zhang, Q., Sun, G., & Zhou, D. (2022) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2022.3200214 · Cited by 57
“As mentioned in [21], the associated pseudo-inverse updating algo-rithm can be defined as where and As a result, the updated weight is defined as where [19], which is a centrifugal multistage impeller blower with key components such as a three-phase induction motor, gearbox, bearing, load, and shaft.”
BackgroundSelf-citationFace Sketch Synthesis Using Regularized Broad Learning System
Li, P., Sheng, B., & Chen, C. L. P. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3070463 · Cited by 56
“We propose a face sketch synthesis method via BLS [22], [23] with a flat network, and the system is refined to adapt to the face sketch synthesis task by a regularized algorithm, which we call regularized BLS (RBLS).”
BackgroundMethodInfluentialSelf-citationGated Broad Learning System Based on Deep Cascaded for Soft Sensor Modeling of Industrial Process
Mou, M., & Zhao, X. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3170967 · Cited by 55
Random Forest Ensemble for River Turbidity Measurement From Space Remote Sensing Data
Gu, K., Zhang, Y., & Qiao, J. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2998615 · Cited by 59
“deep belief network [40], bidirectional ELM (BELM) [41], and broad learning system (BLS) [42].”
BackgroundNiu, B., Liu, J., Duan, P., Li, J., & Yang, D. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2943882 · Cited by 54
The state of health prediction of Li-ion batteries based on an improved extreme learning machine
Hou, X., Guo, X., Yuan, Y., Zhao, K., Liang, T., Yuan, C., & Long, T. (2023) · Journal of Energy Storage · doi:10.1016/j.est.2023.108044 · Cited by 60
Wan, Y., Liu, D., & Ren, J.-C. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102255 · Cited by 54
Spatio-Temporal Interpolated Echo State Network for Meteorological Series Prediction
Xu, M., Yang, Y., Han, M., Qiu, T., & Lin, H. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2869131 · Cited by 55
Jiang, S. B., Wong, P. K., Guan, R., Liang, Y., & Li, J. (2019) · IEEE Access · doi:10.1109/access.2019.2895909 · Cited by 60
“SVD-IBL can reduce the number of enhancement nodes but is unstable.”
BackgroundMethodInfluentialBroad Reinforcement Learning for Supporting Fast Autonomous IoT
Wei, X., Zhao, J., Zhou, L., & Qian, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2980198 · Cited by 60
“It is noted that the effect of weight randomness can be overcome by the incremental learning algorithm as well as feature representation techniques, such as sparse autoencoders [13], fuzzy subsystem [30], etc.”
Chen, L., Li, M., Wu, M., Pedrycz, W., & Hirota, K. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3236320 · Cited by 53
“Broad learning developed by Chen and Liu [20] random vector function-link neural network completes feature representation through horizontal expansion of the network [21].”
BackgroundIntelligent Fingerprint-Based Localization Scheme Using CSI Images for Internet of Things
Zhu, X., Qu, W., Zhou, X., Zhao, L., Ning, Z., & Qiu, T. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3163358 · Cited by 54
“The weight matrix between the nodes and output is computed by ridge regression of the pseudoinverse; readers can refer to [37] for details.”
MethodTask-incremental broad learning system for multi-component intelligent fault diagnosis of machinery
Fu, Y., Cao, H., Chen, X., & Ding, J. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108730 · Cited by 54
Classification of acute myeloid leukemia M1 and M2 subtypes using machine learning
Liu, K., & Hu, J. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105741 · Cited by 57
Shen, D., Lyu, C., Yang, D., Hinds, G., & Wang, L. (2023) · Energy · doi:10.1016/j.energy.2023.127291 · Cited by 53
Feng, S., Ren, W., Han, M., & Chen, Y. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.05.009 · Cited by 56
Broad learning system: Feature extraction based on K-means clustering algorithm
Liu, Z., Zhou, J., & Chen, C. L. P. (2017) · International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS) · doi:10.1109/iccss.2017.8091501 · Cited by 54
“The Broad Learning System is a random vector single-layer neural network with flat functional-link structure, which is a typical RVFLNN.”
BackgroundMethodInfluentialSelf-citationHan, M., Li, W., Feng, S., Qiu, T., & Chen, C. L. P. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3004253 · Cited by 52
“networks and several variants [17], [29], we utilize the random mapping from the leaky integrator reservoir to enhancement layer for complex mapping and quick modeling capacity”
BackgroundMethodInfluentialSelf-citationProgressive Ensemble Kernel-Based Broad Learning System for Noisy Data Classification
Yu, Z., Lan, K., Liu, Z., & Han, G. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3064821 · Cited by 54
“The broad learning system (BLS) [25] is proposed based on RVFL to avoid the above problem by transforming the original features.”
MethodInfluentialSelf-citationAn Ensemble Broad Learning Scheme for Semisupervised Vehicle Type Classification
Guo, L., Li, R., & Jiang, B. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3083508 · Cited by 51
Fractional Approximation of Broad Learning System
Wu, S., Wang, J., Sun, H., Zhang, K., & Pal, N. R. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3127152 · Cited by 52
“Toavoidsome problems of deep architectures, such as time-consuming training due to the large number of parameters and retraining of the network in case the model is not adequate, Chen and Liu [1] proposed a broad learning system (BLS) that allows incremental training if the model is not adequate.”
BackgroundInfluentialGraph embedding deep broad learning system for data imbalance fault diagnosis of rotating machinery
Shi, M., Ding, C., Wang, R., Shen, C., Huang, W., & Zhu, Z. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109601 · Cited by 54
Multiclass Oblique Random Forests With Dual-Incremental Learning Capacity
Chai, Z., & Zhao, C. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2964737 · Cited by 52
“…generalized inverse can be obtained as follows: In BLS, with the mapping and enhancement features and the objective function defined in (5), a simple closed-form solution can be obtained, which enables the BLS to be an effective and fast learner [35] with universal approximation property [38].”
MethodInfluentialBroad learning system for semi-supervised learning
Liu, Z., Huang, S., Jin, W., & Mu, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.059 · Cited by 51
Self-citationDiscriminative group-sparsity constrained broad learning system for visual recognition
Jin, J., Li, Y., Yang, T., Zhao, L., Duan, J., & Chen, C. L. P. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.008 · Cited by 51
Self-citationShieh, J.-L., Haq, Q. M. U., Haq, M. A., Karam, S., Chondro, P., Gao, D.-Q., & Ruan, S.-J. (2020) · Sensors · doi:10.3390/s20236777 · Cited by 59
Adaptive-Robust Fusion Strategy for Autonomous Navigation in GNSS-Challenged Environments
Shen, K., Li, Y., Liu, T., Zuo, J., & Yang, Z. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3315758 · Cited by 51
“Nowadays, NNs and learning have been applied in many fields and have achieved breakthrough successes in large-scale data processing [35], [36], [37].”
BackgroundMethodYuan, X., Chen, J., Zhang, N., Fang, X., & Liu, D. (2021) · China Communications · doi:10.23919/jcc.2021.07.010 · Cited by 54
“Compared with deep learning method, broad learning system (BLS) is a novel efficient and reliable network technology which does not need complex and deep network [8].”
MethodA Robot Motion Learning Method Using Broad Learning System Verified by Small-Scale Fish-Like Robot
Xu, S., Xu, T., Li, D., Yang, C., Huang, C., & Wu, X. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3269773 · Cited by 51
Cui, J. F., Ren, L., Wang, X., & Li, Z. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.03.026 · Cited by 50
Weighted Generalized Cross-Validation-Based Regularization for Broad Learning System
Gan, M., Zhu, H., Chen, G., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3015749 · Cited by 49
Self-citationAdaptive fuzzy control for a marine vessel with time‐varying constraints
Kong, L., He, W., Yang, C., Li, G., & Zhang, Z. (2018) · IET Control Theory and Applications · doi:10.1049/iet-cta.2017.0757 · Cited by 48
Extended Dissipative Filtering for Persistent Dwell-Time Switched Systems With Packet Dropouts
Shen, H., Xing, M., Yan, H., & Park, J. H. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2866632 · Cited by 48
“Theorem 2: Given scalars μ > 1, 0 < λ < 1, b1, b2, α ∈ [0, 1], θ ∈ [0, 1], diagonal matrix Nk = diag{N1k, N2k} and real matrices S1 = ST 1 ≤ 0, S2, S3 = ST 3 > 0, S4 = ST 4 ≥ 0 which satisfy (‖S1‖ + ‖S2‖) · ‖S4‖ = 0, the resulting error system (̃) is exponentially mean-square stable and extended dissipative for any s…”
BackgroundInfluentialBroad learning for nonparametric spatial modeling with application to seismic attenuation
Kuok, S., & Yuen, K. (2019) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12494 · Cited by 49
“The learning network is formulated based on the newly developed broad learning system (Chen & Liu, 2018).”
BackgroundMethodDomain Transfer Broad Learning System for Long-Term Drift Compensation in Electronic Nose Systems
Liu, B., Zeng, X., Tian, F., Zhang, S., & Zhao, L. (2019) · IEEE Access · doi:10.1109/access.2019.2943188 · Cited by 50
Wang, X., Zhu, Y., Han, S., Yang, L., Gu, H., & Wang, F. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3109276 · Cited by 47
Dynamic Neural Network Structure: A Review for its Theories and Applications
Guo, J., Chen, C. L. P., Liu, Z., & Yang, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3377194 · Cited by 58
“Broad learning system (BLS) proposed by Chen and Liu [6] offers a credible alternative to DL.”
Self-citationA Lightweight On-Device Detection Method for Android Malware
Yuan, W., Jiang, Y. X., Li, H., & Cai, M. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2958382 · Cited by 55
“As shown in [18], an alternative way is to solve the problem where A = [ Z n | H ], σ 1 > 0, σ 2 > 0, and ν , μ are typically kinds of norm regularization.”
BackgroundMethodInfluentialGuo, L., Li, R., Jiang, B., & Shen, X. Q. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.08.107 · Cited by 49
Wang, M., Huang, L., & Yang, C. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2981954 · Cited by 47
“Besides, the learning and optimal control problem of discrete-time SFNSs is also an interesting topic [29], [53]–[55].”
BackgroundThe Application of Genetic Algorithm in Land Use Optimization Research: A Review
Ding, X., Zheng, M., & Zheng, X. (2021) · Land · doi:10.3390/land10050526 · Cited by 51
“Chen [89] proposed Broad Learning System (BLS) that aims to offer an”
BackgroundWang, J., Gao, P., Zhang, J., Lu, C., & Shen, B. (2022) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2022.102513 · Cited by 53
A contrastive learning framework enhanced by unlabeled samples for remaining useful life prediction
Kong, Z., Jin, X., Xu, Z., & Chen, Z. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109163 · Cited by 46
Yuan, X., Chen, J., Zhang, N., Ye, Q. J., Li, C., Zhu, C., & Shen, X. (2023) · Engineering · doi:10.1016/j.eng.2023.04.015 · Cited by 53
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.