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 601–700 of 1,000
DACBN: Dual attention convolutional broad network for fine-grained visual recognition
Chen, T., Wang, L., Liu, Y., & Yu, H. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110749 · Cited by 16
A Correntropy-Based Echo State Network with Application to Time Series Prediction
Chen, X., Su, Z., Jin, L., & Li, S. (2025) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2024.124932 · Cited by 15
Tsai, C., Yu, C.-C., & Wu, C.-W. (2019) · Journal of the Chinese Institute of Engineers · doi:10.1080/02533839.2019.1694442 · Cited by 15
“The BLS indeed inherits the major features of the RVFLNN such as universal approximation ability and great generalization performance, but this new type of system can also be extended in a broad sense (Chen and Liu 2018).”
BackgroundMethodPartial label learning based on label distributions and error-correcting output codes
Lin, G., Liu, K., Wang, B., & Zhang, X. (2020) · Soft Computing · doi:10.1007/s00500-020-05203-0 · Cited by 15
“Among that, BLS is an incremental learning algorithm that aims to offer an alternative way of learning in deep structure (Chen and Liu 2018; Zhao et al. 2020).”
BackgroundMethodAn Efficient Anomaly Detection for High-Speed Train Braking System Using Broad Learning System
Wang, C., & Liu, J. (2021) · IEEE Access · doi:10.1109/access.2021.3074929 · Cited by 16
“However, for reaching high accuracy with a deep learning model, a large number of hyperparameters need to be tuned in the training process, making the training process time-consuming [31] This makes it difficult to implement real-time training anomaly detection based on deep learning.”
BackgroundMethodInfluentialDing, W., Tian, Y., Han, S., & Yuan, H. (2021) · IEEE Access · doi:10.1109/access.2021.3084610 · Cited by 15
“To solve this problem, Chen proposed broad learning system (BLS) [7] in 2017 and proved that it has universal approximation capabilities [8].”
BackgroundMethodMulti-Channel Fusion Classification Method Based on Time-Series Data
Jin, X., Yang, A., Su, T., Kong, J., & Bai, Y. (2021) · Sensors · doi:10.3390/s21134391 · Cited by 16
“Based on a random vector functional link NN (RVFLNN) and incremental learning [16], Chen proposed the BLS [17].”
MethodEnhanced Broad Siamese Network for Facial Emotion Recognition in Human–Robot Interaction
Li, Y., Zhang, T., & Chen, C. L. P. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3105621 · Cited by 17
Self-citationYin, L., & Tao, M. (2021) · Energy · doi:10.1016/j.energy.2021.122531 · Cited by 15
A 3D Object Recognition Method From LiDAR Point Cloud Based on USAE-BLS
Tian, Y., Song, W., Chen, L., Fong, S. J., Sung, Y., & Kwak, J. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3140112 · Cited by 15
“Following the computation principle of the classic BLS model, the output matrix γ is computed using Equation (9) [5], where the weight matrix W ∗ is the computation target in the training process of the output layer.”
BackgroundMethodInfluentialYu, K. M., Wang, D., & Li, H. (2021) · International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS) · doi:10.1109/iccss53909.2021.9722026 · Cited by 15
Lai, Q., Vong, C., Wong, P. K., Wang, S. T., Yan, T., Choi, I. C., & Yu, H. H. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108960 · Cited by 15
An efficient robust optimized functional link broad learning system for solar irradiance prediction
Bisoi, R., Dash, D. R., Dash, P. K., & Tripathy, L. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.119277 · Cited by 15
DLBLS_SS: protein secondary structure prediction using deep learning and broad learning system
Yuan, L., Hu, X., Ma, Y., & Liu, Y. (2022) · RSC Advances · doi:10.1039/d2ra06433b · Cited by 18
Liu, J., Wen, T., Xie, G., & Cao, Y. (2022) · Transportation Safety and Environment · doi:10.1093/tse/tdac065 · Cited by 15
Li, X., Zuo, Y., & Jiang, J. (2022) · Sustainability · doi:10.3390/su15010380 · Cited by 15
Zhang, Y., & Yuen, K. (2023) · Engineering Structures · doi:10.1016/j.engstruct.2022.115575 · Cited by 15
Multi-scale broad collaborative filtering for personalized recommendation
Gao, Y., Huang, Z.-W., Huang, Z., Huang, L., Kuang, Y., & Yang, X. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110853 · Cited by 15
Chen, L., Li, M., Wu, M., Pedrycz, W., & Hirota, K. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3301001 · Cited by 16
“BL is adapted to recognize facial emotion in [16].”
BackgroundMethodInfluentialDetecting Network Anomalies and Intrusions in Communication Networks
Rios, A. L. G., Li, Z., Xu, G., Alonso, A. D., & Trajković, L. (2019) · IEEE International Conference on Intelligent Engineering Systems (INES) · doi:10.1109/ines46365.2019.9109448 · Cited by 16
“Module of the BLS algorithm with increments of mapped features, enhancement nodes, and new input data [15].”
MethodInfluentialYin, L., & Lu, Y. (2021) · Energy · doi:10.1016/j.energy.2021.120437 · Cited by 16
Broad Critic Deep Actor Reinforcement Learning for Continuous Control
Thalagala, S., Wong, P. K., Wang, X., & Sun, T. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3554082 · Cited by 14
“This approach is di ff erent from the conventional weight optimization methodologies in typical RL algorithms that involve gradient descent to minimize MSBE.”
Samal, D., Dash, P. K., & Bisoi, R. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02664-0 · Cited by 14
Peng, C., Zhao, L., Meng, F., & Xu, Y. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.108235 · Cited by 14
Cost-Sensitive Broad Learning System for Imbalanced Classification and Its Medical Application
Liang, Y., Wong, P. K., Zhao, B., Wang, Z., Lei, L., Wang, X., & Hu, Y. (2022) · Mathematics · doi:10.3390/math10050829 · Cited by 14
“Hence, according to the Moore–Penrose inverse theory for a partitioned matrix [1], ( Sm+1 )+ is derived as follows, ( Sm+1 )+ = [ (Sm) + − C′B′T B′T ] , (13)”
MethodInfluentialEnsemble deep random vector functional link for self-supervised direction-of-arrival estimation
He, J., Li, X., Liu, P., Wang, L., Zhou, H., Wang, J., & Tang, R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.105831 · Cited by 14
Zhang, D., Kong, L., He, W., & Yu, X. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3271314 · Cited by 14
“By introducing the architecture of BLS [41], an improved method for RBFNNs is presented in this section.”
BackgroundMethodA Fine-Grained Detector of Face Mask Wearing Status Based on Improved YOLOX
Xiao, H., Wang, B., Zheng, J., Liu, L., & Chen, C. L. P. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3300668 · Cited by 14
“The first step is to detect candidate facial regions using a transfer model of Faster_RCNN and InceptionV2 structure, and the second step is to judge the real face masks using a Broad Learning System (BLS) [45].”
MethodSelf-citationChen, Z., Zheng, H., Duan, J., & Wang, X. (2023) · Applied Sciences · doi:10.3390/app132011150 · Cited by 15
Dynamic Model Interpretation-Guided Online Active Learning Scheme for Real-Time Safety Assessment
He, X., & Liu, Z.-Y. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3339242 · Cited by 12
“In [25], Chen and Liu proposed a broad learning system (BLS) with incremental learning capability, which is inherited from the random-vector functional link neuron networks (RVFLNN) [26].”
BackgroundMethodSelf-citationYang, W., Fan, Y., Xu, D., Jiang, B., Yan, X., & Huang, W. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.12.026 · Cited by 14
Wang, S., Ju, Y., Fu, C., Xie, P., & Cheng, C. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3348900 · Cited by 15
“In addition, combined with broad learning, a fast CCA-based FD method is proposed [20].”
Hu, J. Z., Li, H., Li, H., Wu, M., Cao, W., & Pedrycz, W. (2024) · Control Engineering Practice · doi:10.1016/j.conengprac.2024.105850 · Cited by 14
Gu, Z., Shen, Y., Wang, Z., Qiu, J., Li, W., Huang, C., & Jiang, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.107856 · Cited by 14
dHBLSN: A diligent hierarchical broad learning system network for cogent polyp segmentation
Banik, D., Roy, K., Krejcar, O., & Bhattacharjee, D. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112228 · Cited by 15
Telescopic broad Bayesian learning for big data stream
Yuen, K., & Kuok, S. (2024) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13305 · Cited by 14
“Chen et al. (2018) discussed the variations of the flat functional-link network architecture.”
Benchmarking feed-forward randomized neural networks for vessel trajectory prediction
Cheng, R., Liang, M., Li, H., & Yuen, K. F. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109499 · Cited by 15
Salimi-Badr, A., & Parchamijalal, M. M. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112552 · Cited by 14
Chen, G., Shao, W., Tang, F., & Sun, H. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113577 · Cited by 14
Personalized broad learning system for facial expression
Han, J., Xie, L., Liu, J., & Li, X. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-07979-2 · Cited by 16
“TwoimportantparametersintheBLSarethenumberofMFNsandthenumberofENs,whichhavean important impact on the recognition results [2].”
BackgroundMethodInfluentialHand Gesture Recognition: A Survey
Yashas, J., & Shivakumar, G. (2019) · International Conference on Applied Machine Learning (ICAML) · doi:10.1109/icaml48257.2019.00009 · Cited by 14
“An alternate way of learning the deep structure is introduced in [17] called Broad Learning system.”
BackgroundCNN-Based Broad Learning System
Li, T., Fang, B., Qian, J., & Wu, X. (2019) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/siprocess.2019.8868769 · Cited by 14
“Inspired by the feature extraction, a Broad Learning System (BLS) based on the model of RVFLNN is proposed and discussed [5].”
BackgroundMethodHybrid spatial-spectral feature in broad learning system for Hyperspectral image classification
Ma, Y., Liu, Z., & Chen, C. L. P. C. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02320-7 · Cited by 14
Self-citationFuzzy Broad Learning Adaptive Control for Voice Coil Motor Drivers
Hsu, C., Chen, B.-R., & Wu, B. (2022) · International Journal of Fuzzy Systems · doi:10.1007/s40815-021-01227-2 · Cited by 14
“The broad learning system (BLS) first proposed by Chen and Liu [13] offered an alternative way of learning for a deep structure that reduced the time and cost of the training process.”
BackgroundH-BLS: a hierarchical broad learning system with deep and sparse feature learning
Guo, W., Chen, S., & Yuan, X. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03498-0 · Cited by 14
“Besides, for all the four BLS-related algorithms, namely BLS, D&BLS, FBLS and H-BLS, the number of groups of enhancement nodes is set as 1 and the ridge parameter is set as 2 consistently in according to literatures [1, 3, 4, 27].”
BackgroundMethodInfluentialLi, J., Shi, J., Su, H., & Gao, L. (2022) · Electronics · doi:10.3390/electronics11152322 · Cited by 14
Yi, J., An, H., Xing, Y., Li, J., Zhang, G., Bamisile, O., Yang, K., & Xu, Y. (2023) · Energy Reports · doi:10.1016/j.egyr.2022.12.094 · Cited by 14
A Novel Hyperspectral Image Classification Method Using Class-Weighted Domain Adaptation Network
Wang, H., Cheng, Y., & Wang, X. (2023) · Remote Sensing · doi:10.3390/rs15040999 · Cited by 15
Mou, M., Zhao, X., Liu, K., Cao, S., & Hui, Y. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acc47b · Cited by 14
“As a benchmark model for fault detection and diagnosis with complex characteristics, such as nonlinear and dynamics, it is widely used to verify the performance of fault diagnosis models [47, 48] To verify the fault diagnosis performance of the proposed model, we select eight methods as comparison methods: SVM, ANN, B…”
InfluentialZhang, T., Ali, A. E., Wang, C., Zhu, X., & Cesar, P. S. (2019) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3340555.3353716 · Cited by 16
“After mapping the signals into the feature space, BLS [7] is used to classify the valence and arousal.”
MethodWei, H., Zhang, Q., & Gu, Y. (2023) · Sensors · doi:10.3390/s23125642 · Cited by 13
“Chen and Liu [17] used a random vector functional-link neural network and proposed the BLS to overcome the dependence on the deep structure of the DL algorithms.”
BackgroundMethodInfluentialFault Tolerant-Based Broad Fuzzy Neural Control for a Flexible Manipulator With Constraints
Zhao, Z., Feng, K., Liu, Z., Wu, L., Chen, C. L. P., & Yang, C. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3573605 · Cited by 13
Self-citationWang, X., Wang, Z., Yang, S., Wei, S., Wang, T., & Shahzad, M. M. (2026) · Engineering Structures · doi:10.1016/j.engstruct.2026.122261 · Cited by 13
Li, X., Wang, J., & Zhang, B. (2019) · Transactions of the Institute of Measurement and Control · doi:10.1177/0142331219864820 · Cited by 13
A Pseudoinversion-Free Method for Weight Updating in Broad Learning System
Liu, M., Chen, X., Shang, M., & Li, H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3190043 · Cited by 13
“As a result, the one-shot version of BLS [29] is utilized to explore the optimal design.”
BackgroundMethodInfluentialIncremental Embedding Learning With Disentangled Representation Translation
Wei, K., Chen, D., Li, Y., Yang, X., Deng, C. D., & Tao, D. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3199816 · Cited by 16
“Due to the rapid growth of online data and constrained computational resources, incremental learning [3], [4], [5], [6], the goal of which is to gradually learn knowledge from a stream of tasks without forgetting previous tasks, has attracted significant attention in recent years.”
BackgroundActive Broad-Transfer Learning Algorithm for Class-Imbalanced Fault Diagnosis
Liu, G., Shen, W., Gao, L., & Kusiak, A. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3227995 · Cited by 14
“To validate the advantage of ABTCI over the existing BLs in terms of prediction accuracy, four BL variants (BLS [18], RBLS [38], BCNN [23], and DCBLS [39]) were selected due to the same pseudoinverse training strategy.”
BackgroundMethodInfluentialHu, J. Z., Wu, M., Cao, W., & Witold Pedrycz, C. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3270514 · Cited by 15
“In addition, when the predicted performance is not satisfied by the demands or the configuration requires change, new additional nodes or new input data are added to the BLM network via incremental learning [22], [23], thereby improving the model’s performance.”
BackgroundChen, H., Xie, J., Xu, L., Feng, Q., Lin, Q., & Cai, K. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3331026 · Cited by 13
“Then, a new broad layer is formed by flattening these features and input data [23].”
BackgroundDuan, J., Zeng, L., Wu, Y., Chen, L., & Chen, C. L. P. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3373598 · Cited by 15
“Compared to some popular deep NNs, the broad learning system (BLS) [18], an efficient random vector functional-link NN (RVFLNN), offers an alternative approach for large-scale classification problems.”
BackgroundSelf-citationAdaBoost-Stacking Based on Incremental Broad Learning System
Fan, Y., Yu, Z., Yang, K., & Chen, C. L. P. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3433587 · Cited by 13
“However, the traditional As the base classifier of A-IBLS, BLS utilizes its advantage of incremental learning [1] to improve fitting ability by dynamically increasing the number of hidden nodes, when the performance of the original BLS is not good enough in some datasets.”
BackgroundMethodSelf-citationApproximation-Based Admittance Control of Robot-Environment Interaction With Guaranteed Performance
Peng, G., Li, T., Yang, C., & Chen, C. L. P. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3430265 · Cited by 13
“In [26], a fuzzy NN structure with the broad learning system (BLS) [27] is developed, which can automatically adjust NN units to ensure that the trajectory is covered by a compact NN set and satisfy the persistent excitation (PE) condition [28].”
BackgroundSelf-citationImproving the Interpretability Through Maximizing Mutual Information for EEG Emotion Recognition
Yang, H., Chen, C. L. P., Chen, B., & Zhang, T. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3463469 · Cited by 17
Self-citationZhao, Z., Weng, Y., Liu, Z., Yang, C., & Chen, C. L. P. (2024) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2024.3454429 · Cited by 14
“In recent years, a novel network structure known as the broad learning system (BLS), which is characterized by its powerful computational capabilities and groundbreaking developments, has attracted widespread attention [20], [21].”
Self-citationGlobal-local graph convolutional broad network for hyperspectral image classification
Chu, Y., Cao, J., Huang, J., Ju, H., Liu, G., Cao, H., & Ding, W. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.112723 · Cited by 15
Kılıç, K., Atacak, İ., & Doğru, İ. A. (2025) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2024.101945 · Cited by 16
Wu, H., Lin, W., Chen, Y., Shi, F., Shen, W., & Chen, C. L. P. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3530458 · Cited by 13
“B ROAD Learning System (BLS) is a novel neural network proposed by Chen and Liu [1].”
Self-citationNetwork Intrusion Detection for Modern Smart Grids Based on Adaptive Online Incremental Learning
Lu, Q., An, K., Li, J., & Wang, J. (2025) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2025.3535949 · Cited by 19
“BLS, which trains a two-layer broad network, provides an alternative to learn deep structures [26].”
A novel simultaneous monitoring method for surface roughness and tool wear in milling process
Liu, R., & Tian, W. (2025) · Scientific Reports · doi:10.1038/s41598-025-92178-3 · Cited by 13
“BLS is an effective and efficient incremental learning system based on the random vector functional link neural network (RVFLNN) 25 .”
Yan, W., Mei, L.-F., Mo, J., Papadimitriou, C., Yuen, K., & Beer, M. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10688-3 · Cited by 16
Zheng, K., You, Z., Wang, L., Li, Y., Wang, Y.-B., & Jiang, H.-J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-26766-7_36 · Cited by 13
Broad Learning Based Hybrid Beamforming for Mm-Wave MIMO in Time-Varying Environments
Long, Y., Chen, Z., & Murphy, S. (2019) · IEEE Communications Letters · doi:10.1109/lcomm.2019.2952072 · Cited by 13
“Recently, an efficient and effective novel broad learning (BL) is proposed in [7], where the neural network is built in a flat form.”
BackgroundParallel Multistage Wide Neural Network
Xi, J., Ersoy, O. K., Fang, J., Wu, T., Wei, X., & Zhao, C. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3120331 · Cited by 13
“Chen and Liu [12] proposed a broad learning system (BLS) to learn incrementally and effectively without a deep learning structure.”
BackgroundMethodInfluentialData and knowledge driven approach for burden surface optimization in blast furnace
Li, Y., Li, H., Zhang, J., & Zhang, S. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107191 · Cited by 13
An Ensemble Fuzziness-Based Online Sequential Learning Approach and Its Application
Cao, W., Li, S., Huang, C.-C., Wu, Y., Wang, Q., Li, D., & Liu, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-82136-4_21 · Cited by 13
Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search
Ding, Z., Chen, Y.-R., Li, N., Zhao, D., & Chen, C. L. P. (2021) · IEEE Transactions on Systems, Man & Cybernetics. Systems · doi:10.1109/tsmc.2023.3275128 · Cited by 14
“Inspired by random vector functional link neural network (RVFLNN) [27] and incremental learning strategy [28], [29] proposed broad learning system (BLS) and several variants [30].”
Self-citationModular Dynamic Neural Network: A Continual Learning Architecture
Turner, D., Cardoso, P. J. S., & Rodrigues, J. M. F. (2021) · Applied Sciences · doi:10.3390/app112412078 · Cited by 15
“This type of learning problem, learning a new class without retraining the entire network, is known as continual learning (CL) [4], where several other names are also commonly used, such as sequential learning [5], lifelong learning [3] and incremental learning [6].”
BackgroundLi, X., Li, S., Zhou, P., & Chen, G. (2022) · Entropy · doi:10.3390/e24040478 · Cited by 13
“Broad learning system (BLS) is a new kind of shallow neural network based on the random vector functional-link neural twork that is primarily used to tackle the problems of large computation and long training time for deep learning [17].”
BackgroundMethodInfluentialBroad learning system based on the quantized minimum error entropy criterion
Zhang, S., Liu, Z., & Chen, C. L. P. (2022) · Science China Information Sciences · doi:10.1007/s11432-022-3560-8 · Cited by 14
Self-citationRobotic abrasive belt grinding with consistent quality under normal force variations
Chen, G., Yang, J., Yao, K., Xiang, H., & Liu, H. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-10940-1 · Cited by 13
“A BLS is a learning algorithm based on the random vector functional link neural network algorithm [35].”
MethodZhu, J., Jia, M., Zhang, Y., Deng, H., & Liu, Y. (2023) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2023.104778 · Cited by 13
Broad Embedded Logistic Regression Classifier for Prediction of Air Pressure Systems Failure
Adegoke, M., Lee, C. K. M., Chan, J. C., Pang, B., & Alaka, H. (2023) · Mathematics · doi:10.3390/math11041014 · Cited by 14
“The BLS network [8,9] is different from the deep neural network in many aspects, and its structure can be constructed widely.”
Multi-directional broad learning system for the unsupervised stereo matching method
Zhang, Z., Ying, N., Fanman, M., Tiejun, Y., Fan, C., Xiaozhen, R., Wu, R., Kun, C., & Hao-cheng, W. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109648 · Cited by 13
iBT-Net: an incremental broad transformer network for cancer drug response prediction
Zhan, Y., Guo, J., Chen, C. L. P., & Meng, X.-B. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad256 · Cited by 13
Self-citationRobust Broad Learning System for Uncertain Data Modeling
Jin, J., Chen, C. L. P., & Li, Y. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00596 · Cited by 13
“The broad learning system (BLS) [1] is proposed to construct neural networks in a broad sense, which can make the model achieve satisfactory ef cacy in a short time.”
Self-citationShen, H., Huang, Z., Xia, J., Cao, J., & Park, J. H. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2956281 · Cited by 13
“Besides, gene expression depends on the products of the gene in a living cell, protein, some of them regulate the transcription in turn as learning in complex systems [1]–[6] , which is shown in Fig.”
BackgroundA Novel Broad Learning Model-Based Semi-Supervised Image Classification Method
Zheng, J., Yuan, Y., Zhao, H., & Deng, W. (2020) · IEEE Access · doi:10.1109/access.2020.3003916 · Cited by 13
“Broad learning system (BLS) is an efficient incremental learning system proposed [12].”
Background$p$-Norm Broad Learning for Negative Emotion Classification in Social Networks
Chen, G., Peng, S., Zeng, R., Hu, Z., Cao, L., Zhou, Y., Ouyang, Z., & Nie, X. (2022) · Big Data Mining and Analytics · doi:10.26599/bdma.2022.9020008 · Cited by 13
Data-driven Neural Architecture Learning For Financial Time-series ForecastingPreprint
Tran, D. T., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2019) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1903.06751 · Cited by 13
“However, different from SELM, BLS or PLN, HeMLGOP algorithm takes advantage of GOPs to build the neural architecture from a richer set of functionals.”
BackgroundMethodInfluentialImbalanced Broad Learning System with label relaxation and sample weight adaptation
Li, Y., Wang, Y., Jin, J., Zhang, W., Tao, H., Wu, H., & Chen, C. L. P. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113543 · Cited by 12
Self-citationWang, J., Lyu, S., Chen, C. L. P., Zhao, H., Chun, L., & Quan, P. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-021-01897-7 · Cited by 12
“The models used for comparison include BLS (Chen and Liu 2018), CFBLS (Chen et al. 2019), BLS-MS (Huang et al. 2021), Fuzzy BLS (Feng and Chen 2020), F-ELM (Quteishat and Lim 2008), and IF-ELM (Ouyang et al. 2016).”
BackgroundMethodInfluentialSelf-citationNiu, W., Kong, L., Wu, Y., Huang, H., & He, W. (2023) · Robotica · doi:10.1017/s026357472200176x · Cited by 12
“Combining radial basis function neural networks (RBFNNs) and BLS, Huang et al. [27] proposed a novel NNs con-trol for the rigid manipulator system, which realized the approximation of the system model.”
BackgroundMethodInfluentialProgrammable broad learning system for baggage threat recognition
Shafay, M., Ahmed, A. H., Hassan, T., Dias, J. M. M., & Werghi, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16057-7 · Cited by 12
“BLS is a flat network that maps the original input into an array of feature nodes [32].”
TransBLS: transformer combined with broad learning system for facial beauty prediction
Gan, J., Xie, X., He, G., & Luo, H. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04931-8 · Cited by 12
“The broad learning system (BLS) is a fast incremental learning system without a deep architecture that is composed of feature and enhancement nodes, a weight layer and an output layer [23].”
BackgroundBandgap prediction of ABX3-type perovskites using Broad Learning System
Tian, T., Li, T., Li, G., Hao, F., Tang, R., Yuan, Z., & Liu, X. (2023) · Materials Today Communications · doi:10.1016/j.mtcomm.2023.107026 · Cited by 15
A Lightweight Multidendritic Pyramidal Neuron Model With Neural Plasticity on Image Recognition
Zhang, Y., Cai, P., Sun, Y., Zhang, Z., Lei, Z., & Gao, S. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3379968 · Cited by 16
“…attention-based bidirectional long short-term memory network (Bi-LSTM) [60], broad learning system for multilayer perceptron-based method (BLS) [61], deep subdomain adaptation network (DSAN) [62], the white-box MLP-based dendrite net (DD) [63], Alexnet [63], and novel single-source domain…”
BackgroundIncremental and sequence learning algorithms for weighted regularized extreme learning machines
Zhang, Y., Dai, Y., & Li, J. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05470-6 · Cited by 12
“In fact, this random learning theory can be traced back to the literatures [3] and [4], and in recent years it has been continuously mined and widely used in extreme learning machines, stochastic configuration networks [5], and broad learning systems (BLS) [6].”
Broad learning system based on maximum multi-kernel correntropy criterion
Zhao, H., & Lu, X. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106521 · Cited by 12
Generalized Maximum Correntropy Broad Learning System With Robust M-Estimator
Zhao, H., Lu, X., & Chen, C. L. P. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3462801 · Cited by 12
“To this end, Chen and Liu [2] introduced the broad learning system (BLS).”
Self-citationTransferable and discriminative broad network for unsupervised domain adaptation
Zhang, L., Yu, Z., Yang, K., Wang, B., & Chen, C. L. P. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113297 · Cited by 13
Self-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.