The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.
Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture
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 401–500 of 1,000
Yi, J., Huang, J., Zhou, W., Chen, G., & Zhao, M. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3143079 · Cited by 25
“Recently, an impressive randomized neural network named the BLS was developed [27], and it avoids the inherent challenge of a deep network structure through the broad expansion of both the feature nodes and the enhancement nodes.”
BackgroundTian, W., Zhao, F., Min, C., Feng, X., Liu, R., Mei, X., & Chen, G. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3144232 · Cited by 25
“To this end, an efficient and effective incremental learning technique called broad learning system (BLS) with a simpler structure of the flat network was introduced in [28].”
MethodLavanya, K., V, Karnick, S., Ghalib, M. R., Shankar, A., Khapre, S. P., & Tayubi, I. A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12613-9 · Cited by 25
“This system is proposed because deep-learning agonizes from a onerous training process due to a large number of connecting parameters in filters and layers [3].”
BackgroundMultitarget Stochastic Configuration Network and Applications
Wang, Q., Hong, Q., Wu, S., & Dai, W. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3162570 · Cited by 25
“[13] M. Sahani and P. K. Dash, “FPGA-based online power quality disturbances monitoring using reduced-sample HHT and class-specific weighted RVFLN,” IEEE Trans.”
BackgroundInfluentialModal-Regression-Based Broad Learning System for Robust Regression and Classification
Liu, L., Liu, T., Chen, C. L. P., & Wang, Y. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3256999 · Cited by 28
“To this end, Chen and Liu [5] proposed a novel flat artificial neural network named as broad learning system (BLS), which expands its structure in a broad manner rather than the deep way.”
BackgroundMethodInfluentialSelf-citationOnline Measurement of Dioxin Emission in Solid Waste Incineration Using Fuzzy Broad Learning
Xia, H., Tang, J., Yu, W., & Qiao, J. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3259419 · Cited by 25
Shen, X., Dai, Q., & Ullah, W. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119103 · Cited by 26
Duan, J., Yao, S., Tan, J., Liu, Y., Chen, L., Zhang, Z., & Chen, C. L. P. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3347888 · Cited by 25
Self-citationFormulating Ensemble Learning of SVMs Into a Single SVM Formulation by Negative Agreement Learning
Zhou, J., Jiang, Z., Chung, F.-L., & Wang, S. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2958647 · Cited by 27
Process monitoring of batch process based on overcomplete broad learning network
Peng, C., & Lu, R. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.104139 · Cited by 25
Deng, T., Huang, Y., Han, G., Shi, Z., Lin, J., Dou, Q., Liu, Z., Guo, X., Chen, C. L. P., & Han, C. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3403927 · Cited by 27
“Then an independent broad learning inference system ( [21], [28]) serves for fast inference.”
Self-citationIncremental Learning-Enabled Fault Diagnosis of Dynamic Systems: A Comprehensive Review
Liu, Z., He, X. Y., Huang, B., & Zhou, D. (2025) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3586643 · Cited by 26
“…(RNNet) structures, represented by random vector functional-link neural network (RVFL) [66], extreme learning machine (ELM) [67], and broad learning system (BLS) [68], have been used to design diagnostic model architectures considering their good incremental update capabilities [69], [70], [71].”
Self-citationSentiment Analysis Using Autoregressive Language Modeling and Broad Learning System
Gong, X., Jin, J., & Zhang, T. (2019) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm47256.2019.8983025 · Cited by 25
“Recently, C.L.Philip Chen et al. [12] proposed an efficient incremental neural network called Broad Learning System (BLS) to handle the high dimensional data by extracting features.”
MethodInfluentialHyperspectral image classification with discriminative manifold broad learning system
Chu, Y., Lin, H., Yang, L., Sun, S., Diao, Y., Min, C., Fan, X., & Shen, C. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.120 · Cited by 24
Incremental Bayesian broad learning system and its industrial application
Liu, Y., Wang, Y., Chen, L., Zhao, J., Wang, W., & Liu, Q. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09929-z · Cited by 24
Cauchy regularized broad learning system for noisy data regression
Liu, L., Cai, L., Liu, T., Chen, C. L. P., & Tang, X. (2022) · Information Sciences · doi:10.1016/j.ins.2022.04.051 · Cited by 26
Self-citationLiu, Z., Han, H., Yang, H., & Qiao, J. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3197204 · Cited by 24
“To further illustrate the identification performance, the results of DFBLS are compared with other models: BLS [27], fuzzy BLS (FBLS) [28], fuzzy neural network BLS (FNN-BLS) [29], incremental BLS (IBLS) [30], and T2F-BLS.”
MethodSelf-citationDu, J., Liu, P., Vong, C., Chen, C., Wang, T., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3259016 · Cited by 29
“…random weights and bias for calculating Z p and H p are then concatenated together to generate the final features H for input X Hence, according to [26], the connecting weight W equals to and Moreover, BLS also works for incremental learning of feature nodes, enhancement nodes, and input data.”
BackgroundMethodSelf-citationSource-Free Domain Adaptation (SFDA) for Privacy-Preserving Seizure Subtype Classification
Zhao, C., Peng, R., & Wu, D. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3274563 · Cited by 29
“Inspired by broad learning system [24], which randomly generates and fixes the input weights of the hidden layer, both U-TrBoosting and SS-TrBoosting generate a random feature mapping (RFM) h k in each iteration to introduce feature randomness into the training process and speed-up the training,…”
MethodPeng, C., Xu, Y. B., Meng, F., & Xiong, W. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3324971 · Cited by 24
“Chen et al. introduced the broad learning system (BLS), which aims at tackling the previously mentioned and accelerating network training and updating rapidly, all while sustaining comparatively low time overhead [12].”
BackgroundRich Feature Combination for Cost-Based Broad Learning System
Zhang, T.-L., Chen, R., Yang, X., & Guo, S. (2018) · IEEE Access · doi:10.1109/access.2018.2885164 · Cited by 26
“[54] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, ‘‘Densely connected convolutional networks,’’ in Proc.”
BackgroundMethodInfluentialGao, J., Shen, L., & Gao, L. (2019) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3612 · Cited by 24
Lin, J., Liu, Z., Chen, C. L. P., & Zhang, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.059 · Cited by 24
Self-citationAdversarial transfer learning for cross-domain visual recognition
Wang, S., Zhang, L., & Fu, J. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106258 · Cited by 29
Transfer of semi-supervised broad learning system in electroencephalography signal classification
Zhou, Y., She, Q., Ma, Y., Kong, W., & Zhang, Y. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05793-2 · Cited by 26
Fault diagnosis of rolling bearing based on multiscale one-dimensional hybrid binary pattern
Cao, S., Xu, F., & Ma, T. (2021) · Measurement · doi:10.1016/j.measurement.2021.109552 · Cited by 24
Remaining Useful Life Prediction Based on Incremental Learning
Que, Z., Jin, X., Xu, Z., & Hu, C. (2023) · IEEE Transactions on Reliability · doi:10.1109/tr.2023.3294939 · Cited by 23
Cai, L., Yin, H., & Lin, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3353535 · Cited by 23
“Additionally, our method is also compared with some competitive meth-ods including SVM [41], artificial neural network (ANN), SAE, deep belief network (DBN), BLS [42], CNN [43], and BCNN [19].”
Li, P., Jin, Q., Liu, H., Han, L., Li, C., & Luo, Y. (2024) · LWT · doi:10.1016/j.lwt.2024.116570 · Cited by 23
Power System Transient Stability Assessment Based on Spatio-Temporal Broad Learning System
Zhao, H., & Ni, R. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3522369 · Cited by 24
“Recently, an emerging discriminative learning method named broad learning system (BLS) [22] has been proposed.”
Li, S., Zhou, B., Shang, J., Chen, X., & Yu, J. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.07.002 · Cited by 29
Broad Learning Model Based on Enhanced Features Learning
Qing-mei, Z., & He, X. (2019) · IEEE Access · doi:10.1109/access.2019.2905528 · Cited by 25
“According to the dynamic update algorithm of the Functional-Link Neural Network [10], the pseudoinverse of Am+a is”
MethodInfluentialCharging Diagnosis of Power Battery Based on Adaptive STCKF and BLS for Electric Vehicles
Wang, M., Ge, Q., Li, C., & Sun, C. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3171766 · Cited by 23
Broad learning for early diagnosis of Alzheimer's disease using FDG-PET of the brain
Duan, J., Liu, Y., Wu, H., Wang, J., Chen, L., & Chen, C. L. P. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1137567 · Cited by 27
“The BLS is a lightweight network with a broad structure proposed by Chen and Liu (2017).”
BackgroundSelf-citationLiu, Y., Zhou, H., Guan, M., Feng, F., & Duan, J. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3263433 · Cited by 24
A spectral-ensemble deep random vector functional link network for passive brain–computer interface
Li, R., Gao, R., Suganthan, P. N., Cui, J., Sourina, O., & Wang, L. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120279 · Cited by 24
Multi-surrogate framework with an adaptive selection mechanism for production optimization
Wang, J., Zhang, L., Zhang, K., Wang, J., Zhou, J.-P., Peng, W.-F., Yin, F., Zhong, C., Yan, X., Liu, P., et al. (2023) · Petroleum Science · doi:10.1016/j.petsci.2023.08.028 · Cited by 23
Deep Broad Learning for Emotion Classification in Textual Conversations
Peng, S., Zeng, R., Liu, H., Cao, L., Wang, G., & Xie, J. (2023) · Tsinghua Science & Technology · doi:10.26599/tst.2023.9010021 · Cited by 25
Wang, X., Zhang, G., Niu, B., Wang, D., & Wang, X. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3341845 · Cited by 25
“This topic originated in various phenomena in the biological world, such as flying of bees, flocking of wild geese, dolphin groups and so on [1], [2], [3], [4], [5], [6], [7], [8].”
BackgroundDiscriminative elastic-net broad learning systems for visual classification
Li, Y., Jin, J., Geng, Y., Xiao, Y., Liang, J., & Chen, C. L. P. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111445 · Cited by 23
Self-citationLin, J., Liu, Z., Chen, C. L. P., & Zhang, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.017 · Cited by 23
Self-citationDrought Prediction Method Based on an Improved CEEMDAN-QR-BL Model
Liu, Y., & Li-hu, W. (2021) · IEEE Access · doi:10.1109/access.2020.3048745 · Cited by 23
“As it ensures that the function approximation method has a good generalisation ability, the BL method effectively eliminates the shortcomings of long training processes [19]–[22], while exhibiting a stronger generalisation ability and efficiency than those of the neural networks.”
MethodMultiscale Random Convolution Broad Learning System for Hyperspectral Image Classification
Ma, Y., Liu, Z., & Chen, C. L. P. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3060876 · Cited by 23
Self-citationKnowledge Transfer for Face Verification Using Heterogeneous Generalized Operational Perceptrons
Tran, D. T., Serkan Kiranyaz, B., Gabbouj, M., & Iosifidis, A. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8804296 · Cited by 22
“Besides HeMLGOP 1, we also evaluated the performance of other progressive learning algorithms, namely I-ELM [14], S-ELM [15], BLS [16], and PLN [17].”
MethodInfluentialThree-domain fuzzy wavelet broad learning system for tremor estimation
Lin, J., Liu, Z., Chen, C. L. P., & Zhang, Y. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105295 · Cited by 22
Self-citationKuok, S., Yuen, K., Roberts, S., & Girolami, M. (2020) · Structural Health Monitoring · doi:10.1177/1475921720916923 · Cited by 22
A novel WWH problem-based semi-supervised online method for sensor drift compensation in E-nose
Liang, Z., Zhang, L., Tian, F., Wang, C., Yang, L., Guo, T., & Xiong, L. Y. (2021) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2021.130727 · Cited by 22
BNAS-v2: Memory-Efficient and Performance-Collapse-Prevented Broad Neural Architecture Search
Ding, Z., Chen, Y.-R., Li, N., & Zhao, D. (2022) · IEEE Transactions on Systems, Man & Cybernetics. Systems · doi:10.1109/tsmc.2022.3143201 · Cited by 18
“Structure of BLS [30]. feature fusion .”
MethodInfluentialTimber damage identification using dynamic broad network and ultrasonic signals
Zhang, Y., Yuen, K., Mousavi, M., & Gandomi, A. H. (2022) · Engineering Structures · doi:10.1016/j.engstruct.2022.114418 · Cited by 22
Broad Learning Framework for Search Space Design in Rayleigh Wave Inversion
Yang, X.-H., Han, P., Yang, Z., Miao, M., Sun, Y., & Chen, X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3208616 · Cited by 27
“As suggested by Chen and Liu [29], the sparse autoencoder is adopted to obtain compressed data for realizing the function φ.”
BackgroundMethodInfluentialTree Broad Learning System for Small Data Modeling
Xia, H., Tang, J., Yu, W., & Qiao, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216788 · Cited by 23
“The BLS can adaptively increase the width of the model in terms of its feature, neural nodes, and input samples, avoiding the time-cost problem caused by the deep stacking structure [16].”
BackgroundMethodResultHyperspectral image classification via active learning and broad learning system
Huang, H., Liu, Z., Chen, C. L. P., & Zhang, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-021-02805-5 · Cited by 22
“Due to the disadvantages such as many paramenters involved, complex models and long time consuming, traditional deep learning is replaced by a simple and efficient BLS [27–29].”
Self-citationActive federated transfer algorithm based on broad learning for fault diagnosis
Liu, G., Shen, W., Gao, L., & Kusiak, A. (2023) · Measurement · doi:10.1016/j.measurement.2023.112452 · Cited by 22
Guo, L., Ren, Y., Li, R., & Jiang, B. (2023) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2023.3266791 · Cited by 22
Water Table and Permeability Estimation From Multi‐Channel Seismoelectric Spectral Ratios
Hu, K., Ren, H., Huang, Q., Zeng, L., Butler, K. E., Jougnot, D., Linde, N., & Holliger, K. (2023) · Journal of Geophysical Research Solid Earth · doi:10.1029/2022jb025505 · Cited by 22
“The BL system proposed by Chen and Liu (2017) is a flat neural network with a single lateral layer neural network, in contrast to deep structured neural networks.”
BackgroundMethodInfluentialCompact Broad Learning System Based on Fused Lasso and Smooth Lasso
Chu, F., Liang, T., Chen, C. L. P., Wang, X., & Ma, X. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3267947 · Cited by 23
“This section only briefly described the BLS algorithms; hence, the readers are referred to [1] for further details of the modeling procedure and the corresponding incremental learning algorithm.”
MethodSelf-citationZhang, B., Chen, Z., Yan, R., Lai, B., Wu, G., You, J., Wu, X., Duan, J., & Zhang, S. (2023) · Academic Radiology · doi:10.1016/j.acra.2023.07.002 · Cited by 23
A multi-feature-based fault diagnosis method based on the weighted timeliness broad learning system
Hu, W., Wang, Y., Li, Y., Wan, X., & Gopaluni, R. B. (2024) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2023.12.071 · Cited by 22
Lu, T., Xiong, J., Zhou, J., Wang, Q., Cen, J., Liu, M., Zhang, Q., Dai, Q., Zhang, T., & Zhang, J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3373075 · Cited by 22
Adaptive Broad Deep Reinforcement Learning for Intelligent Traffic Light Control
Zhu, R., Wu, S., Li, L., Ding, W., Lv, P., & Sui, L. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3401829 · Cited by 22
“Broad RL (BRL) [13] can achieve fast remodeling to alleviate issues caused by time-consuming modeling, utilizing the broad learning system (BLS) [14] and the RL mechanism to generate policies.”
BackgroundMethodZhang, S., Kong, L., Qi, S., Jing, P., He, W., & Xu, B. (2019) · Nonlinear Dynamics · doi:10.1007/s11071-018-4629-8 · Cited by 22
Active broad learning system for ECG arrhythmia classification
Fan, W., Si, Y., Yang, W., & Zhang, G. (2021) · Measurement · doi:10.1016/j.measurement.2021.110040 · Cited by 22
Zhao, F., Liu, Y., Liu, H., & Fan, J. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117015 · Cited by 22
Xie, H., Ding, Y., Qian, Y., Tiwari, P., & Guo, F. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121157 · Cited by 21
Lei, C., Guo, J., & Chen, C. L. P. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3403953 · Cited by 21
“BLS [14], [15], [16], [28] is an alternative model to DNNs.”
BackgroundMethodSelf-citationA partial domain adaptation broad learning system for machinery fault diagnosis
Qin, A., Hu, Q., Zhang, Q., & Mao, H. (2024) · Measurement · doi:10.1016/j.measurement.2024.116437 · Cited by 22
Ali, S. G., Chen, Y., Sheng, B., Li, H., Wu, Q., Yang, P., Muhammad, K., & Yang, G. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09303-9 · Cited by 21
Yang, Z., & Huang, Y. J. (2021) · Evolutionary Intelligence · doi:10.1007/s12065-020-00532-3 · Cited by 21
Chen, L., Li, M., Lai, X., Hirota, K., & Witold Pedrycz, C. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.2754 · Cited by 21
Graph-based broad learning system for classification
Liu, Z., Huang, S., Jin, W., & Mu, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.065 · Cited by 21
Self-citationA broad learning-based comprehensive defence against SSDP reflection attacks in IoTs
Liu, X., Zheng, L., Helal, S., Zhang, W., Jia, C., & Zhou, J. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.02.008 · Cited by 21
Fan, W., Si, Y., Yang, W., & Sun, M. (2022) · Measurement · doi:10.1016/j.measurement.2022.111412 · Cited by 21
Broad fuzzy cognitive map systems for time series classification
Wu, K., Yuan, K., Teng, Y., Liu, J., & Jiao, L. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109458 · Cited by 23
A Novel Rolling Bearing Fault Diagnosis Method Based on BLS and CNN with Attention Mechanism
Wang, X., Hua, T., Xu, S. Y., & Zhao, X. (2023) · Machines · doi:10.3390/machines11020279 · Cited by 23
Yu, D., Kang, Q. K., Jin, J., Wang, Z., & Li, X. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109656 · Cited by 21
Lai, Q., Zhou, J., Gan, Y., Vong, C., & Chen, C. L. P. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2023.3287978 · Cited by 21
“To our best knowledge, there is no such simultaneous learning mechanism of diverse correlations for MIML in existing works as summarized in Table I. Recently, an efficient discriminative learning called Broad Learning System (BLS) [20] was proposed.”
BackgroundInfluentialSelf-citationA Lightweight Malware Traffic Classification Method Based on a Broad Learning Architecture
Zhang, Y., Gui, G., & Mao, S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3297210 · Cited by 22
“To address these problems, this letter explores a broad learning (BL) [3]-based MTC method (termed BL-MTC), which is a lightweight solution without using a graphics processing unit (GPU).”
MethodIncremental Collaborative Beam Alignment for Millimeter Wave Cell-Free MIMO Systems
Zhang, C., Chen, L., Zhang, L., Huang, Y., & Zhang, W. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3306889 · Cited by 21
“…coding of to construct the n -th label for the learning model y Recall that the BL model is established as a flat network, where the original inputs are transferred and positioned as “mapped features” in the feature nodes, while the structure is expanded broadly in the “enhancement nodes” [22].”
BackgroundMethodLai, Q., Vong, C., Yan, T., Wong, P. K., & Liang, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125362 · Cited by 22
DWnet: Deep-wide network for 3D action recognition
Dang, Y., Yang, F., & Yin, J. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103441 · Cited by 22
Zheng, K., You, Z., Wang, L., Li, Y., Zhou, J.-R., & Zeng, H.-T. (2020) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2020.3013837 · Cited by 23
“Broad Learning System based on Random Vector Functional Link Neural Network (RVFLNN) effectively eliminates the shortcoming of too long training process, and also ensures excellent generalization ability [37].”
MethodInfluentialTsai, C., Chan, C.-C., Li, Y., & Tai, F. (2020) · International Journal of Fuzzy Systems · doi:10.1007/s40815-020-00913-x · Cited by 21
Jia, R., Zhang, S., & You, F. (2021) · Control Engineering Practice · doi:10.1016/j.conengprac.2021.104853 · Cited by 21
A Novel Regression Prediction Method for Electronic Nose Based on Broad Learning System
Wang, Y., Jia, P., Cui, H., & Peng, X. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3090449 · Cited by 21
2FDP-BRL: A New Framework of Distributed Task Offloading for IoAV in Extreme Weather Scenarios
Peng, X., Song, S., Zhang, X., Dong, M., Ota, K., & Xu, L. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3604461 · Cited by 20
“Broad Learning Systems (BLS), introduced in [21], offer a simplified neural network framework that builds on and enhances the capabilities of the Random Vector Functional Link Neural Network (RVFLNN).”
Tang, L., Liu, C., Jiyin Liu, B., & Wang, X. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2962880 · Cited by 20
“Some data analytics methods [18]–[20] have been used to describe the internal structure of black-box models, and some global optimization algorithms based on statistical models have been used to solve some expensive problems [21].”
MethodMulti‐resolution broad learning for model updating using incomplete modal data
Kuok, S., & Yuen, K. (2020) · Structural Control and Health Monitoring · doi:10.1002/stc.2571 · Cited by 22
Broad learning robust semi-active structural control: A nonparametric approach
Kuok, S., Yuen, K., Girolami, M., & Roberts, S. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108012 · Cited by 24
Guo, J., Liu, Z., Chen, C. L. P., Zhang, T., Wang, L., & Fan, K. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3110517 · Cited by 20
“whereA is pseudoinverse matrix computed by ridge regression approximation [5].”
BackgroundMethodInfluentialSelf-citationReal-Time Charging Risk Assessment for Electric Vehicles Based on Improved Broad BP-AHP
Ge, Q., Qiao, H., Li, C., Yang, Q., & Jiang, H. (2021) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2021.3111591 · Cited by 20
Bag dissimilarity regularized multi-instance learning
Huang, S., Liu, Z., Jin, W., & Mu, Y. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108583 · Cited by 20
Self-citationXie, R., Vong, C., Chen, C. L. P., & Wang, S. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3146983 · Cited by 20
“When k varies from 1 to 3, which means that the ignorance of the output weights of shared feature nodes becomes more and more, the testing classification accuracies by re_RST&BLS_ k on MNIST and the testing regression errors (in RMSE) by re_RST&BLS_ k on PY become worse although the corresponding training accuracies by…”
BackgroundMethodResultInfluentialSelf-citationArtificial Intelligence Oceanography
Li, X., & Wang, F. (2023) · Springer eBooks · doi:10.1007/978-981-19-6375-9 · Cited by 27
An evolutionary ensemble convolutional neural network for fault diagnosis problem
Najaran, M. H. T. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120678 · Cited by 24
FPGA-based remote target classification in hyperspectral imaging using multi-graph neural network
Chellaswamy, C., Manjula, M. M., Ramasubramanian, B., & Sriram, A. (2024) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2024.105008 · Cited by 21
Zhang, A., Qian, X., Xu, C., & Zhang, J. (2024) · IEEE Access · doi:10.1109/access.2024.3356824 · Cited by 20
Locally Directional and Extremal Pattern for Texture Classification
Dong, Y., Wang, T., Yang, C., Zheng, L., Song, B., Wang, L., & Jin, M. (2019) · IEEE Access · doi:10.1109/access.2019.2924985 · Cited by 20
“Building an effective texture representation method is a key step in many computer vision tasks, including object recognition [3]–[5], visual navigation [6]–[8], image segmentation [9]–[12], image retrieval [13]–[17], scene understanding [18]–[21], industrial inspection [22]–[25] etc.”
Spectral-Spatial Joint Classification of Hyperspectral Image Based on Broad Learning System
Zhao, G., Wang, X., Kong, Y., & Cheng, Y. (2021) · Remote Sensing · doi:10.3390/rs13040583 · Cited by 20
“Experimental Comparison In order to prove the advantages of SSBLS on the three real datasets, we compare SSBLS with SVM [65], HiFi-We [42], SSG [66], spectral-spatial hyperspectral image classification with edge-preserving filtering (EPF) [41], support vector machine based on the Gaussian filter (GSVM), feature extrac…”
BackgroundMethodA Deep Branch-Aggregation Network for Recognition of Gas–Liquid Two-Phase Flow Structure
Gao, Z., Qu, Z., Cai, Q., Hou, L., Liu, M., & Tao, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3022188 · Cited by 20
Parhi, P., Bisoi, R., & Dash, P. K. (2022) · IEEE Access · doi:10.1109/access.2022.3170038 · Cited by 19
“In BLS, the input data are mapped to generate feature nodes then the mapped feature nodes are expanded to form the enhancement nodes where the weights are randomly generated [36].”
Method
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.