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 501–600 of 1,000
Greedy stochastic configuration networks for ill-posed problems
Zhou, T., Wang, Y., Yang, G., Zhang, C., & Wang, J. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110464 · Cited by 19
Peng, C., Xu, Y., & FanChao, M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120958 · Cited by 19
Meng, J., Huo, X., Zhao, H., Zhang, G., Zhang, L., Wang, X., Lin, J., & Zhou, S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106234 · Cited by 20
Sajid, M., Sharma, R. K., Beheshti, I., Tanveer, M., & Initiative, A. D. N. (2024) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1546 · Cited by 26
“In addressing the “black-box” nature of artificial neural networks (ANNs), especially in critical applications like healthcare, where interpretability is crucial, we take neuro NF-BLS Feng & Chen (2020).”
InfluentialHua, M., Zhang, Y., Zhang, Q., Tang, H., Guo, L., Lin, Y., Sari, H., & Gui, G. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3481902 · Cited by 19
“Therefore, we focus more on the novel Broad Learning (BL) approach proposed by Chen and Liu [20], Liu et al. [21], and Chen et al. [22].”
BackgroundIdentification of Coal Geographical Origin Using Near Infrared Sensor Based on Broad Learning
Lei, M., Rao, Z., Li, M., Yu, X., & Zou, L. (2019) · Applied Sciences · doi:10.3390/app9061111 · Cited by 19
Liu, P., Wang, X., Yin, L., & Liu, B. (2020) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-020-01136-0 · Cited by 20
Jia, X., Zhang, T., Chen, C. L. P., Liu, Z., Chen, L., Wen, G., & Hu, B. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283159 · Cited by 23
“Broad Learning System (BLS) proposed by Chen et al. [19] is a kind of flat network, where the inputs are mapped to the feature nodes, and the mapped features are enhanced to the enhancement nodes.”
BackgroundMethodSelf-citationZhang, M., Hu, T., Wu, L., Kang, G., & Guan, Y. (2021) · Energy · doi:10.1016/j.energy.2021.120959 · Cited by 19
Wang, C., Gao, J., Li, H., Lin, C., Beck, J. L., & Huang, Y. (2022) · Structural Health Monitoring · doi:10.1177/14759217221104224 · Cited by 20
“Recently, a broad learning system (BLS) on a single hidden-layer neural network was proposed, 20,21 and the fi tting generalization performance for any nonlinear function was theoretically proven in Ref.”
A decomposition-ensemble broad learning system for AQI forecasting
Zhan, C., Jiang, W., Lin, F., Zhang, S., & Li, B. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07448-2 · Cited by 21
Mixture-of-experts-based broad learning system and its applications
Wang, J., Nie, L., Duan, J., Zhao, H., & Chen, C. L. P. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126389 · Cited by 18
Self-citationHow Deep Is Deep Enough for Deep Belief Network for Approximating Model Predictive Control Law
Wang, G., Qiao, J., Liu, C., & Shen, Z. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2021.3074984 · Cited by 18
“In particular, these methods used in comparison are NN-based MPCs, including BLS-MPC [40], SODBN-MPC [41], DRNN-MPC [42], CC-RNN-MPC [37], DNN-MPC [43], DFNN-MPC [44], SOFNN-MPC [45], systematic min–max optimization-based MPC (SMMO-MPC) [46], and robust output feedback tracking control (ROF-TC) [47].”
MethodResultInfluentialA Gesture-Based Natural Human–Robot Interaction Interface With Unrestricted Force Feedback
Liang, Y., Du, G., Li, C., Chen, C., Wang, X., & Liu, P. X. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3149109 · Cited by 20
“where Wei and βei are fine-tuned random matrix and vector with autoencoder [42], whose elements are drawn from uniform distribution on the interval [−1, 1].”
BackgroundMethodInfluentialSelf-citationBroad Learning System Using Rectified Adaptive Moment Estimation for Harmonic Detection and Analysis
Li, C., Sun, C., Chen, Z., & Zhang, Y. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3270503 · Cited by 18
“As an alternative to deep learning, broad learning system (BLS) [38] is put forward on the basis of the random vector functional link neural network.”
MethodInfluentialA Broad Generative Network for Two-Stage Image Outpainting
Zhang, Z., Weng, H., Zhang, T., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3264617 · Cited by 19
“In recent years, BLS has been widely used in supervised classification tasks [22], [41], [42], [43], [44], [45] and has outperformed some popular deep learning methods.”
BackgroundMethodInfluentialSelf-citationLocal sensitive discriminative broad learning system for hyperspectral image classification
Cao, H., Song, C., Chu, Y., Zhao, C., Deng, M., & Liu, G. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106307 · Cited by 18
Zuo, G., Zhou, J., Gong, D., & Huang, G. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3277102 · Cited by 18
“In recent years, the broad learning system (BLS) has become widely used [19], [20], [21], [22].”
BackgroundHuang, Z., & Duan, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106763 · Cited by 18
A Broad Ensemble Learning System for Drifting Stream Classification
Bakhshi, S., Ghahramanian, P., Bonab, H., & Can, F. (2023) · IEEE Access · doi:10.1109/access.2023.3306957 · Cited by 22
“Based on the original BLS paper [9], the broad model is defined as follows: The ultimate goal of the system is to find W by solving a least square problem.”
BackgroundMethodInfluentialA Robust Semi-Supervised Broad Learning System Guided by Ensemble-Based Self-Training
Guo, J., & Chen, C. L. P. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3393020 · Cited by 19
“It can be calculated by where A + is pseudo-inverse matrix computed by ridge regression approximation [7].”
BackgroundMethodSelf-citationAn Incremental-Self-Training-Guided Semi-Supervised Broad Learning System
Guo, J., Liu, Z., & Chen, C. L. P. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3392583 · Cited by 22
“The BLS proposed by Chen and Liu [7] successfully addresses the issue of parameter optimization and high time consumption in the deep architectural model, providing an efficient idea.”
InfluentialSelf-citationNan, J., Dai, W., Yuan, G., & Zhou, P. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3423487 · Cited by 18
“To solve this problem, a dynamic gradual update method based on the iteration theory of Greville [34], [35], [36], [37] was proposed to extend ICA into a lightweight version, called ICA+. 2) ICA+: Given f : R d → R m , if the hidden layer of the ICA+ has L − 1 nodes, it can be expressed as (cid:7)…”
Interactive multi-agent convolutional broad learning system for EEG emotion recognition
Shi, S., Liu, W., & Chen, C. L. P. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125420 · Cited by 20
Self-citationFunctional-Link Neural Network for Nonlinear Equalizer in Coherent Optical Fiber Communications
Zhang, J., Lei, P., Hu, S., Zhu, M., Yu, Z., Xu, B., & Qiu, K. (2019) · IEEE Access · doi:10.1109/access.2019.2947278 · Cited by 19
“where λ represents the further constraints on the sum of the squared weights [23].”
Cai, C., Liu, S., Wang, L., Yang, B., Zhi, M., Wang, R., & He, W. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914437 · Cited by 18
“Although these deep structures of CNN make better performance, researchers suffer from the time consumption problem [12], and the features extracted may not be optimal features [13].”
BackgroundMethodWang, Y., Wang, C., Kang, S., Xie, J., Wang, Q., & Микулович, В. И. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/ab8fee · Cited by 18
“The broad learning system (BLS) is a new learning algorithm proposed by Professor Chen of the University of Macau [26].”
MethodFuzzy Broad Learning System Based on Accelerating Amount
Zou, W., Xia, Y., & Dai, L. (2021) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2021.3128210 · Cited by 18
“In order to improve the generalization ability and reduce the training timeofneuralnetwork,ChenandLiu[1]proposebroadlearningsystem (BLS),whichisbasedonthenotionofrandomvectorfunctional-link neuralnetwork(RVFLNN)[2].”
MethodWong, P. K., & Biao, J. S. (2021) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2021.3125767 · Cited by 19
“For BL, its activation function is also set to sigmoid function [24].”
BackgroundMethodInfluentialExploring high-order correlations with deep-broad learning for autism spectrum disorder diagnosis
Hao, X., An, Q., Li, J., Min, H., Guo, Y., Yu, M. Z., & Qin, J. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.1046268 · Cited by 20
“It represents a step towards building more effective machine learning methods that can further extend models based on deep learning methods and improve the learning efficiency of the models (Chen and Liu, 2018; Gong et al., 2022).”
BackgroundLiu, Z.-Y., & He, X. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3294788 · Cited by 20
“Restrictions apply. where Then the updated weight at time t can be defined as [44] Nevertheless, under the rules of floating-point computations , it is difficult to achieve = 0 precisely in most actual scenarios.”
BackgroundInfluentialSelf-citationMohamed, A., Rashid, M. E., & Shaalan, K. F. (2025) · IEEE Access · doi:10.1109/access.2025.3575303 · Cited by 32
Wu, G., & Duan, J. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105323 · Cited by 17
“With good feature representation of sparse autoencoder and the advantages of random vector functional link neural network (RVFLNN), BLS can achieve better performance in classification problem (Chen and Liu, 2017).”
A survey of large-scale graph-based semi-supervised classification algorithms
Song, Y., Zhang, J., & Zhang, C. (2022) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2022.10.002 · Cited by 24
Lu, Z., Wang, N., Li, Q., & Yang, C. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.11.076 · Cited by 17
A Hybrid Model for Billet Tapping Temperature Prediction and Optimization in Reheating Furnace
Yu, H. Z., Gong, J., Wang, G., & Chen, X. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3221219 · Cited by 17
“Thus, deep learning technology has been widely used in the prediction optimization problems in process industry [7], [8].”
MethodGong, X., Dong, Y., & Zhang, T. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01964-w · Cited by 25
“Moreover, some studies have found that flat neural networks such as Broad Learning System (BLS) [29, 30] are also very suitable for EEG emotion recognition tasks and have achieved outstanding results.”
Lyu, S., Li, F., Yang, W., Zhang, Q., Su, J., Zhao, R., & Lu, X. (2024) · Journal of Analytical Atomic Spectrometry · doi:10.1039/d3ja00406f · Cited by 17
Yao, L., Zhao, B., Wang, Q., Wang, Z., Zhang, P., Qi, X., Wong, P. K., & Hu, Y. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3371375 · Cited by 17
Xiang, Y., Lu, X., Cai, D., Chen, J., & Bao, C. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-13734-1 · Cited by 17
“Due to its advantages, such as low sample requirements, fast training speed, and high fitting accuracy, the broad learning system (BLS) [10] is more in line with the current trend of small-batch part processing in the mechanical manufacturing field and is increasingly being applied in engineering…”
Multiobjective Evolution of the Deep Fuzzy Rough Neural Network
Zhao, J., Chang, D., Cao, B., Liu, X., & Lv, Z. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3397728 · Cited by 17
Simplified Kernel-Based Cost-Sensitive Broad Learning System for Imbalanced Fault Diagnosis
Yang, K., Chen, W., Shi, Y., Yu, Z., & Chen, C. L. P. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3478191 · Cited by 17
Self-citationDai, H., Huang, Y., Zhu, L., Lin, H., Hui, Y., Lai, Y., & Yang, Y. (2025) · Journal of Power Sources · doi:10.1016/j.jpowsour.2025.236544 · Cited by 21
Broad Forest: A Non-Neural Network Style Broad Model for Streaming Video QoE Evaluation
Wei, X., Xia, H., & Zhou, L. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2974811 · Cited by 17
“, is used to offer an alternative way of learning in deep structure [6].”
MethodIdentification of Dynamical Systems Using a Broad Neural Network and Particle Swarm Optimization
Han, R., Wang, R., & Zeng, G. (2020) · IEEE Access · doi:10.1109/access.2020.3009982 · Cited by 17
Soft sensor modeling for fraction yield of crude oil based on ensemble deep learning
Yi, L., Lu, J. Y., Ding, J., Liu, C., & Chai, T. (2020) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2020.104087 · Cited by 17
Broad Learning Enhanced 1H-MRS for Early Diagnosis of Neuropsychiatric Systemic Lupus Erythematosus
Li, Y., Ge, Z., Zhang, Z., Shen, Z., Wang, Y., Zhou, T., & Wu, R. (2020) · Computational and Mathematical Methods in Medicine · doi:10.1155/2020/8874521 · Cited by 17
“Broad learning systems are an alternative way to address the time-consuming training process and nonconvex issues, especially when the structure is insufficient to model the system [28].”
BackgroundEmotion Classification of Text Based on BERT and Broad Learning System
Peng, S., Zeng, R., Liu, H., Chen, G., Wu, R., Yang, A., & Yu, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85896-4_30 · Cited by 17
Zhao, H., Wu, Y., & Deng, W. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3485438 · Cited by 16
Unsupervised Feature Selection for High-Order Embedding Learning and Sparse Learning
Hu, Z., Wang, J., Mańdziuk, J., Ren, Z., & Pal, N. R. (2025) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3546658 · Cited by 16
“Finally, to prove the generality of the proposed co-competitive optimization strategy, we apply it to some related models, i.e., RR [51], BLS [52] and fuzzy BLS (FBLS) [53], and compare their performance with that of the corresponding original methods.”
Downsizing and enhancing broad learning systems by feature augmentation and residuals boosting
Xie, R., & Wang, S. (2020) · Complex & Intelligent Systems · doi:10.1007/s40747-020-00139-2 · Cited by 16
LINPE-BL: A Local Descriptor and Broad Learning for Identification of Abnormal Breast Thermograms
Pramanik, S., Bhattacharjee, D., Nasipuri, M., & Krejcar, O. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3101453 · Cited by 16
Yin, L., & Lu, Y. (2021) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2021.107861 · Cited by 17
Programmable Broad Learning System to Detect Concealed and Imbalanced Baggage Threats
Shafay, M., Hassan, T., Ahmed, A. H., Velayudhan, D., Dias, J. M. M., & Werghi, N. (2022) · International Conference on Digital Futures and Transformative Technologies (ICoDT2) · doi:10.1109/icodt255437.2022.9787420 · Cited by 16
Adaptive slow feature analysis - sparse autoencoder based fault detection for time-varying processes
Tan, S., Zhou, X., Shi, H., & Song, B. (2022) · Journal of the Taiwan Institute of Chemical Engineers · doi:10.1016/j.jtice.2022.104599 · Cited by 16
Model-Free Formation Control of Autonomous Underwater Vehicles: A Broad Learning-Based Solution
Cao, W., Yan, J. J., Yang, X., Luo, X., & Guan, X. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123165 · Cited by 16
Efficient Incremental Offline Reinforcement Learning With Sparse Broad Critic Approximation
Yao, L., Zhao, B., Xu, X., Wang, Z., Wong, P. K., & Hu, Y. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3305498 · Cited by 16
“The broad learning system (BLS) is designed based on the concept of random vector functional-link (RVFL) networks, and it processes the input data via two steps in a random manner with activation functions, resulting in mapping features and enhancement nodes, respectively [13].”
MethodA Novel Fuzzy Echo State Broad Learning System for Surface Roughness Virtual Metrology
Tian, W., Zhang, J., Zhao, F., Jiang, G., Mei, X., Chen, G., & Wang, H. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3310747 · Cited by 16
“To address these drawbacks, Chen and Liu [29] designed a rapid BLS without neither the tedious iteration training nor the stacking structure.”
MethodWhen Broad Learning System Meets Label Noise Learning: A Reweighting Learning Framework
Liu, L., Chen, J., Yang, B., Feng, Q., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3317255 · Cited by 17
“1 and more details can be found in [8].”
Self-citationLi, C., Hu, Q., Zhao, S., Wu, J., & Xiong, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107508 · Cited by 16
UNFIS: A Novel Neuro-Fuzzy Inference System with Unstructured fuzzy rules
Salimi-Badr, A. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127437 · Cited by 20
Robust Incremental Broad Learning System for Data Streams of Uncertain Scale
Zhong, L., Chen, C. L. P., Guo, J., & Zhang, T. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3396659 · Cited by 20
“Restrictions apply. in [12].”
InfluentialSelf-citationZhu, C., Xie, Y., Yang, H., Li, Z., Hu, L., & Xu, K. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108433 · Cited by 16
Generative broad Bayesian (GBB) imputer for missing data imputation with uncertainty quantification
Kuok, S., Yuen, K., Dodwell, T. J., & Girolami, M. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112272 · Cited by 16
Lyu, S., Li, F., Yang, W., Zhang, Q., & Wang, Q. (2024) · Talanta · doi:10.1016/j.talanta.2024.127213 · Cited by 16
Li, R.-B., Niu, B., Feng, Z., Li, J., Duan, P., & Yang, D. (2019) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2019.09.019 · Cited by 16
Lu, C., Zhang, X., Wu, M., Han, Q., & He, Y. M. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2957810 · Cited by 16
Feng, L., Zhao, C., Chen, C. L. P., Li, Y., Zhou, M., Qiao, H., & Fu, C. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.100 · Cited by 16
Self-citationBroad Echo State Network for Channel Prediction in MIMO-OFDM Systems
Sui, Y., He, Y., Cheng, T., Huang, Y., & Ning, S. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3025913 · Cited by 17
“Fortunately, the aforementioned drawbacks of the deep learning methods can be mitigated and even overcome by the broad learning idea [26].”
BackgroundLi, J., Hua, C., & Yang, Y. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.3031525 · Cited by 16
Facial Beauty Prediction via Local Feature Fusion and Broad Learning System
Zhai, Y., Yu, C., Qin, C., Zhou, W., Ke, Q., Gan, J., Labati, R. D., Piuri, V., & Scotti, F. (2020) · IEEE Access · doi:10.1109/access.2020.3032515 · Cited by 18
Li, J., Yang, Z., Gao, L., & Li, X. (2021) · IEEE Access · doi:10.1109/access.2021.3076683 · Cited by 16
“To solve the aforementioned problem, Chen and Liu [10] proposed a broad learning system (BLS); specifically, a random vector functional link neural network.”
BackgroundHyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks
Rosato, A., Panella, M., & Kleyko, D. V. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533805 · Cited by 16
“For instance, in [57] a distributed classification is studied, based on the Broad Learning System [58], which is quite complex in its computation, since it involves optimizing the Broad Learning System via Alternative Direction Method of Multipliers (ADMM).”
MethodOnline robust echo state broad learning system
Guo, Y., Yang, X., Wang, Y., Wang, F., & Chen, B. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.099 · Cited by 16
Noise/fault aware regularization for incremental learning in extreme learning machines
Wong, H. T., Leung, H. C., Leung, C.-S., & Wong, E. W. M. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.11.026 · Cited by 16
Wong, P. K., Yao, L., Yan, T., Choi, I. C., Yu, H. H., & Hu, Y. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103476 · Cited by 16
Yu, B., Zhang, Y., Wang, X., Gao, H., Sun, J., & Gao, X. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103566 · Cited by 16
Broad learning system based ensemble deep model
Zhang, C., Ding, S., Guo, L., & Zhang, J. (2022) · Soft Computing · doi:10.1007/s00500-022-07004-z · Cited by 17
“To evaluate the regression accuracy of EDBLS, we use EDBLS compare with RVFL (Pao and Takefuji 1992; Pao et al. 1994), SCN (Wang and Li 2017a) and BLS (Chen and Liu 2018, 2017; Chen et al. 2019).”
BackgroundMethodResultInfluentialHou, Z., Shen, H., Zhou, X., Gu, J., Wang, Y., & Zhao, T. (2022) · Frontiers of Computer Science · doi:10.1007/s11704-022-0625-8 · Cited by 22
Learning broad learning system with controllable sparsity through L0 regularization
Chu, F., Wang, G., Wang, J., Chen, C. L. P., & Wang, X. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110068 · Cited by 16
Self-citationAn Experimental Analysis of Deep Neural Network Based Classifiers for Sentiment Analysis Task
Shukla, M., & Kumar, A. (2023) · IEEE Access · doi:10.1109/access.2023.3266640 · Cited by 17
“They used the broad learning system approach suggested by Chen and Liu [39] on top of the multitask deep learning network for the task of classification in sentiment analysis.”
MethodLearning to Rank: A Progressive Neural Network Learning Approach
Tran, D. T., & Iosifidis, A. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683711 · Cited by 16
“BLS [18] 0.”
MethodZhong, D., & Liu, F. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.01.080 · Cited by 17
Hyperspectral image classification based on local binary pattern and broad learning system
Zhao, G., Wang, X., & Cheng, Y. (2020) · International Journal of Remote Sensing · doi:10.1080/01431161.2020.1798553 · Cited by 16
DGCB-Net: Dynamic Graph Convolutional Broad Network for 3D Object Recognition in Point Cloud
Tian, Y., Chen, L., Song, W., Sung, Y., & Woo, S. (2020) · Remote Sensing · doi:10.3390/rs13010066 · Cited by 16
“Our proposed broad network structure was inspired by the basic broad learning system [31], as shown in Figure 3.”
BackgroundMethodXiong, H., Chen, G., Ren, H., & Li, H. (2025) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2024.124929 · Cited by 15
Interpretable research of fuzzy methods: A literature survey
Zhang, K., Shao, T., Sun, Y., Xu, X., Zhang, X., Zhou, X., Ding, K., & Huang, S. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103524 · Cited by 26
Ren, C., & Xu, Y. H. (2020) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2019.1371 · Cited by 15
“To address the real-time DSA model updating problem, this study proposes an incremental broad learning method for accuracy maintenance and improvement of the data-driven DSA models [30–32].”
MethodPeng, C., Zhang, R., & Chunhao, D. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117390 · Cited by 15
Semisupervised Manifold Regularization via a Subnetwork-Based Representation Learning Model
Zhang, W., Wu, Q. M. J., & Yang, Y. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3177573 · Cited by 15
Two-stage broad learning inversion framework for shear-wave velocity estimation
Yang, X.-H., Han, P., Yang, Z., & Chen, X. (2022) · Geophysics · doi:10.1190/geo2022-0060.1 · Cited by 15
Chen, S., Li, X., Liang, Y., Lu, X., Huang, Y., Zhu, J., & Li, J. (2022) · Medicine · doi:10.1097/md.0000000000031399 · Cited by 12
“BLS [18] is a deep structure neural network model based on Random Vector Functional-link Neural Network.”
Meng, X.-B., Chen, C. L. P., & Li, H. (2022) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2022.3212419 · Cited by 15
“With shallow architecture and pseudoinverse learning algorithm, BLS has fast learning and inference speed [22], and thus can be a good candidate to construct the reduced-order model for online application.”
BackgroundMethodSelf-citationA Mechanical Equipment Fault Diagnosis Model Based on TSK Fuzzy Broad Learning System
Wang, X., Wang, C., Zhu, K., & Zhao, X. (2022) · Symmetry · doi:10.3390/sym15010083 · Cited by 16
Network intrusion detection via tri-broad learning system based on spatial-temporal granularity
Li, J., Zhang, H., Liu, Z., & Liu, Y. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-022-05025-x · Cited by 15
“Recently, an innovative randomized neural network–broad learning system (BLS) has been proposed by Chen and Liu [10], which is based on the flat network architecture [11].”
BackgroundMethodSelf-citationDevelopment and validation of a deep-broad ensemble model for early detection of Alzheimer's disease
Ma, P., Wang, J., Zhou, Z., Chen, C. L. P., & Duan, J.-W. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1137557 · Cited by 12
Self-citationLiu, X., Qin, X., Zhou, M., Sun, H., & Han, S. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3321384 · Cited by 16
Li, C., Hu, Q., Zhao, S., Wu, J., Xiong, J., & Zhang, Q. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3337120 · Cited by 15
“The core is finding the pseudoin-verse target values of feature nodes and enhanced nodes [41].”
BackgroundInfluentialXia, H., Tang, J., Yu, W., & Qiao, J. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3357896 · Cited by 15
Fast and Accurate Quality Prediction for Injection Molding: An Improved Broad Learning System Method
Lin, J., Ren, Z., Wu, Z., Ouyang, Z., & Yang, A. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3346849 · Cited by 15
“Recently, the broad learning system (BLS) has been proposed by Chen and Liu [22], which is a flat network based on the idea of random vector functional link neural networks (RVFLNN).”
Background
Metadata
- Authors
- Chen, C. L. P., & Liu, Z.
- Affiliations
- Chinese Academy of Sciences (CN)
- University of Macau (MO)
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2018-01
- Volume
- 29
- Issue
- 1
- Pages
- 10-24
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2738226240
- Cited by
- 1,957
- References
- 58
- Citations by year
- 2026: 177 · 2025: 312 · 2024: 303 · 2023: 255 · 2022: 270 · 2021: 223 · 2020: 177 · 2019: 158 · 2018: 73
- FWCI
- 68.00
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Neural Networks and Learning Systems (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Fundo para o Desenvolvimento das Ciências e da Tecnologia (019/2015/A1)
- UM Research Grants
- National Nature Science Foundation of China (61572540)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and ELM
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- broad learning system, incremental learning, flat network architecture, network expansion, model reduction, singular value decomposition, object recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.