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
Chen, X., Zhang, H., Wu, C., Mao, S., Ji, Y., & Bennis, M. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2876279 · Cited by 680
Universal Approximation Capability of Broad Learning System and Its Structural Variations
Chen, C. L. P., Liu, Z., & Feng, S. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2866622 · Cited by 549
“Hence, only the increment of the additional enhancement nodes is available here, and the algorithm is similar to the corresponding section of the original BLS in [3].”
BackgroundMethodInfluentialSelf-citationChen, H., Jiang, B., Ding, S. X., & Huang, B. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3029946 · Cited by 521
Fuzzy Broad Learning System: A Novel Neuro-Fuzzy Model for Regression and Classification
Feng, S., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2857815 · Cited by 490
“BLS [28] is an improved flat framework [29] which inherits the major feature and superiority of a random vector functional-link NN [30].”
BackgroundSelf-citationA Review of Fault Detection and Diagnosis for the Traction System in High-Speed Trains
Chen, H., & Jiang, B. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2897583 · Cited by 413
“1: Preprocess Zς based on step 1 in Algorithm 1 as Zς ; 2: Project Zς into obtained principal and residual subspaces in step 2 in Algorithm 1 as T̂ς and T̃ς ; 3: Define Tς = [T̂ς T̃ς ] as the mapped feature nodes of Zς ; 4: Obtain the enhancement nodes Hς of Zς [126]; 5: Output the ς -th type of fault features ς based…”
MethodGCB-Net: Graph Convolutional Broad Network and Its Application in Emotion Recognition
Zhang, T., Wang, X., Xu, X., & Chen, C. L. P. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2019.2937768 · Cited by 396
Self-citationUnderwater Internet of Things in Smart Ocean: System Architecture and Open Issues
Qiu, T., Zhao, Z., Zhang, T., Chen, C., & Chen, C. L. P. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2946618 · Cited by 393
“can learn network state and environment parameters adaptively, such as reinforcement learning [57], broad learning [58], deep learning [59], decision tree [60], and self-organizing map [61].”
BackgroundSelf-citationResearch Review for Broad Learning System: Algorithms, Theory, and Applications
Gong, X., Zhang, T., Chen, C. L. P., & Liu, Z. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3061094 · Cited by 350
“Three different scenarios, including the incremental enhancement nodes, mapping feature nodes, and new input data, can Algorithm 1: Basic BLS [17] Input : training samples X ; number of feature maps n ; number of groups of enhancement nodes m ; satisfy the various requirements and applications.”
BackgroundMethodInfluentialSelf-citationAdaptive Neural Network Control of a Flapping Wing Micro Aerial Vehicle With Disturbance Observer
He, W., Yan, Z., Sun, C., & Chen, Y. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2720801 · Cited by 328
“We need to further design more appropriate controllers to realize ultimate objects on an ongoing current basis [15]–[21].”
BackgroundAdvancements in Humanoid Robots: A Comprehensive Review and Future Prospects
Tong, Y., Liu, H., & Zhang, Z. (2024) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.124140 · Cited by 288
A Survey on the New Generation of Deep Learning in Image Processing
Jiao, L., & Zhao, J. (2019) · IEEE Access · doi:10.1109/access.2019.2956508 · Cited by 293
“The parameters of F-BLS consist of the weights connecting the outputs of the enhancement layer to the final output layer and the coefficients in the following part of fuzzy rules in every fuzzy subsystem, which can be calculated by pseudoinverse rapidly.”
MethodInfluentialZhang, X., Chan, K. W., Li, H., Wang, H., Qiu, J., & Wang, G. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2975134 · Cited by 301
“Various neural networks (NNs), including randomized learning NN [42], shallow NN [43], deep-learningbased NN [44], and NN without deep architecture [45], have been used in the forecasting studies.”
MethodYu, W., & Zhao, C. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2931255 · Cited by 295
“[32] proposed a broad learning system (BLS) based on the random vector functional-link neural network (RVFLNN) [33] to solve these issues in DNN methods.”
MethodGraph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
Ahmedt-Aristizabal, D., Armin, M. A., Denman, S., Fookes, C., & Petersson, L. (2021) · Sensors · doi:10.3390/s21144758 · Cited by 272
“search for more powerful features in both deep and broad spaces [136].”
BackgroundMethodRecurrent Broad Learning Systems for Time Series Prediction
Xu, M., Han, M., Chen, C. L. P., & Qiu, T. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2863020 · Cited by 284
“…contains n groups of feature nodes and m groups of enhancement nodes, and we can expand the network by adding the ( n + 1 ) th group of feature nodes to the new state matrix where are the additional output of the enhancement nodes corresponding to the ( n + 1 ) th group of feature nodes [31].”
BackgroundMethodInfluentialSelf-citationZhao, S., Zhang, C., & Wang, Y. (2022) · Journal of Energy Storage · doi:10.1016/j.est.2022.104901 · Cited by 259
Semi-Supervised Broad Learning System Based on Manifold Regularization and Broad Network
Zhao, H., Zheng, J., Deng, W., & Song, Y. (2020) · IEEE Transactions on Circuits and Systems I: Regular Papers · doi:10.1109/tcsi.2019.2959886 · Cited by 247
“Broad learning system (BLS) is an emerging network proposed by Chen and Liu [5].”
BackgroundIndoor Intelligent Fingerprint-Based Localization: Principles, Approaches and Challenges
Zhu, X., Qu, W., Qiu, T., Zhao, L., Atiquzzaman, M., & Wu, D. O. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3014304 · Cited by 245
“In view of the time-consuming problem of training the model, we believe that the BLS can be used as an emerging technical solution, which was proposed by CLP Chen and Liu [129].”
MethodBaGFN: Broad Attentive Graph Fusion Network for High-Order Feature Interactions
Xie, Z., Zhang, W., Sheng, B., Li, P., & Chen, C. L. P. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3116209 · Cited by 237
“In this article, we introduce the BLS theory to construct a new broad attention module, which can achieve the efficient refinement of high-order feature interactions at a bitwise level.”
BackgroundMethodInfluentialSelf-citationLithium-ion batteries remaining useful life prediction based on BLS-RVM
Chen, Z., Shi, N., Ji, Y., Niu, M., & Wang, Y. (2021) · Energy · doi:10.1016/j.energy.2021.121269 · Cited by 197
Du, J., Vong, C.-M., & Chen, C. L. P. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2969705 · Cited by 194
“According to [23], the connecting weights for this broad structure are W = A†Y, which can be easily computed through ridge regression approximation as follows: A† = (ATA)−1AT (4)”
BackgroundMethodInfluentialSelf-citationChen, X., Wu, C., Chen, T., Zhang, H., Liu, Z., Zhang, Y., & Bennis, M. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2963667 · Cited by 187
“6The tradeoff between the performance improvement and the time spent for the offline training process with a more complex neural network architecture is still an open problem [51], [52].”
BackgroundSelf-citationNiu, B., Liu, Y., Zhou, W., Li, H., Duan, P., & Li, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2906372 · Cited by 165
Asymmetric Bounded Neural Control for an Uncertain Robot by State Feedback and Output Feedback
Kong, L., He, W., Dong, Y., Cheng, L., Yang, C., & Li, Z. (2019) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2019.2901277 · Cited by 164
Motor Learning and Generalization Using Broad Learning Adaptive Neural Control
Huang, H., Zhang, T., Yang, C., & Chen, C. L. P. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2950853 · Cited by 165
“Recently, a novel framework of a broad learning system (BLS) based on incremental learning principle has been developed and successfully applied for pattern recognition and offline classification [12], [13].”
BackgroundSelf-citationATT Squeeze U-Net: A Lightweight Network for Forest Fire Detection and Recognition
Zhang, J., Zhu, H., Wang, P., & Ling, X. (2021) · IEEE Access · doi:10.1109/access.2021.3050628 · Cited by 179
“To further evaluate the recognition performance of our network model, we compare it against four different deep convolutional networks SqueezeNet9 [3], ResNet 5010 [39], VGG 1611 [25], BLS12 [40], MobileNet-Fire [41], EMN-Fire [28] and Muhammad et al.”
MethodOptimal Robot–Environment Interaction Under Broad Fuzzy Neural Adaptive Control
Huang, H., Yang, C., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2998984 · Cited by 164
“Recently, a novel framework called the broad learning system (BLS) [20], which is developed from random vector functional-link neural networks (RVFLNNs) [21], has been proposed and extensively utilized 2168-2267 c (cid:2) 2020 IEEE.”
BackgroundInfluentialSelf-citationMa, Y., Wu, L., Guan, Y., & Peng, Z. (2020) · Journal of Power Sources · doi:10.1016/j.jpowsour.2020.228581 · Cited by 164
On the origins of randomization-based feedforward neural networks
Suganthan, P. N., & Katuwal, R. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107239 · Cited by 158
Li, G., Zhang, A., Zhang, Q., Wu, D., & Zhan, C. (2022) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2022.3160266 · Cited by 153
Neural Networks-Based Fault Tolerant Control of a Robot via Fast Terminal Sliding Mode
Zhang, S., Yang, P., Kong, L., Chen, W., Fu, Q., & Peng, K. (2021) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2019.2933050 · Cited by 150
Deep Learning-Based Model Predictive Control for Continuous Stirred-Tank Reactor System
Wang, G., Jia, Q., Qiao, J., Bi, J., & Zhou, M. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3015869 · Cited by 153
Memari, M., Shakya, P., Shekaramiz, M., Seibi, A. C., & Masoum, M. A. S. (2024) · IEEE Access · doi:10.1109/access.2024.3371493 · Cited by 175
“A novel model, CBNLM-BLS, is introduced that combines chunking and Non-Local Means (NLMs) [128] to enhance the Broad Learning System (BLS) [129], making it more computationally efficient.”
MethodWeighted Broad Learning System and Its Application in Nonlinear Industrial Process Modeling
Chu, F., Liang, T., Chen, C. L. P., Wang, X., & Ma, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2935033 · Cited by 153
“By the discussion in [15], the pseudoinverse of the new expanded input matrix can be deduced as”
BackgroundMethodInfluentialSelf-citationDeep learning in robotics: survey on model structures and training strategies
Karoly, A. I., Galambos, P., Kuti, J., & Rudas, I. J. (2021) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2020.3018325 · Cited by 146
“Based on the RVFLNN method Chen and Liu [23], [24] also introduced broad learning systems, that offer an incremental training strategy for the fast adaptation and retraining of such models.”
MethodRegularized robust Broad Learning System for uncertain data modeling
Jin, J., & Chen, C. L. P. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.09.028 · Cited by 149
Self-citationStacked Broad Learning System: From Incremental Flatted Structure to Deep Model
Liu, Z., Chen, C. L. P., Feng, S., Feng, Q., & Zhang, T. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.3043147 · Cited by 149
“In [15], the BLS offers an alternative frame for constructing deep networks based on the idea of Random Vector Functional Link Neural Networks (RVFLNN) [24] and incremental learn-”
BackgroundMethodInfluentialSelf-citationOmnidirectional mobile robots, mechanisms and navigation approaches
Taheri, H., & Zhao, C. X. (2020) · Mechanism and Machine Theory · doi:10.1016/j.mechmachtheory.2020.103958 · Cited by 152
Wang, J., Yang, C., Shen, H., Cao, J., & Rutkowski, L. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2979860 · Cited by 138
NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search
Wei, C., Niu, C., Tang, Y., Wang, Y., Hu, H., & Liang, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3151160 · Cited by 164
“Besides the above search strategies, the extreme learning machine (ELM) [37], [38] and broad learning system (BLS) [39] can also be used to design the structure of neural networks automatically.”
MethodLeveraging Deep Reinforcement Learning for Traffic Engineering: A Survey
Xiao, Y., Liu, J., Wu, J., & Ansari, N. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3102580 · Cited by 162
Multi-Tenant Cross-Slice Resource Orchestration: A Deep Reinforcement Learning Approach
Chen, X., Zhao, Z., Wu, C., Bennis, M., Liu, H., Ji, Y., & Zhang, H. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2933893 · Cited by 134
“With the consideration 11 The tradeoff between the time spent during the training process and a performance improvement with a deeper and/or wider neural network is still an open problem [38].”
BackgroundHan, M., Feng, S., Chen, C. L. P., Xu, M., & Qiu, T. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2866149 · Cited by 142
“eral aspects in recent years[10], [24], [25], [26].”
BackgroundMethodInfluentialSelf-citationNiu, B., Li, H., Zhang, Z., Li, J., Hayat, T., & Alsaadi, F. E. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2866519 · Cited by 134
Crack detection using fusion features‐based broad learning system and image processing
Zhang, Y., & Yuen, K. (2021) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12753 · Cited by 138
“It has the advantages of short training time (Chen & Liu 2017; S. Feng & Chen, 2018).”
BackgroundBMT-Net: Broad Multitask Transformer Network for Sentiment Analysis
Zhang, T., Gong, X., & Chen, C. L. P. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3050508 · Cited by 145
“Hence, Chen et al. [27]–[30] provided an alternative framework [i.e., the broad learning system (BLS)] for data classification and regression problems.”
MethodSelf-citationImproving Video Temporal Consistency via Broad Learning System
Sheng, B., Li, P., Ali, R., & Chen, C. L. P. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3079311 · Cited by 134
“can update the input data or feature nodes with time [25], [27]–[29].”
BackgroundSelf-citationXu, S., Liu, J., Yang, C., Wu, X., & Xu, T. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3121080 · Cited by 129
“Since the broad learning method (an artificial NN-based method) has the advantages of the simple to apply, flexible adjustment with new data and fast training [46], we use the BLS method for controller design.”
BackgroundMethodInfluentialData-Driven Designs of Fault Detection Systems via Neural Network-Aided Learning
Chen, H., Chai, Z., Dogru, O., Jiang, B., & Huang, B. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3071292 · Cited by 129
B2-ViT net: broad vision transformer network with broad attention for seizure prediction
Shi, S., & Liu, W. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3346955 · Cited by 124
Wang, X., Zhang, T., Xu, X., Chen, L., Xing, X., & Chen, C. L. P. (2018) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621147 · Cited by 132
“As a kind of flat network, the broad learning model [18] is aim to expand network in a broad way.”
BackgroundSelf-citationNeural Learning Control of Strict-Feedback Systems Using Disturbance Observer
Xu, B., Shou, Y., Luo, J. T., Pu, H., & Shi, Z. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2862907 · Cited by 124
“Neural networks (NNs) [9], support vector machine [10], and broad learning technique [11] can be used for data analysis and application.”
Niu, B., Wang, D., Liu, M., Song, X., Wang, H., & Duan, P. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2952108 · Cited by 121
Domain Knowledge-Based Deep-Broad Learning Framework for Fault Diagnosis
Feng, J. Y., Yao, Y., Lu, S., & Liu, Y. (2020) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2020.2982085 · Cited by 125
“To this end, DL-based methods are employed to hold strong feature extraction ability, and a BLS is introduced to gain flexibility of the framework when it comes to homologous multitask problems that need to update diagnosis models.”
BackgroundMethodInfluentialDiscriminative graph regularized broad learning system for image recognition
Jin, J., Liu, Z., & Chen, C. L. P. (2018) · Science China Information Sciences · doi:10.1007/s11432-017-9421-3 · Cited by 125
Self-citationQiao, H., Chen, J., & Huang, X. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3071312 · Cited by 129
Analysis and Variants of Broad Learning System
Zhang, L., Li, J., Lu, G., Shen, P., Bennamoun, M., Shah, S. A. A., Miao, Q., Zhu, G., Li, P., & Lu, X. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2995205 · Cited by 129
A new learning paradigm for random vector functional-link network: RVFL+
Zhang, P., & Yang, Z.-X. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.09.039 · Cited by 124
Incremental Weighted Ensemble Broad Learning System for Imbalanced Data
Yang, K., Yu, Z., Chen, C. L. P., Cao, W., You, J., & Wong, H. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3061428 · Cited by 121
Self-citationMemory-Efficient Class-Incremental Learning for Image Classification
Zhao, H., Wang, H., Fu, Y., Wu, F., & Li, X. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3072041 · Cited by 109
“Recently, there have been a lot of research works on incremental learning with deep models [33]–[46].”
Broad Learning System Based on Maximum Correntropy Criterion
Zheng, Y., Chen, B., Wang, S., & Wang, W. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3009417 · Cited by 119
Ye, M., Chen, C. L. P., & Zhang, T. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3225855 · Cited by 134
“Zhang et al. [24] utilized ChebyNet to explore the deeper-level information of graph-structured data and adopted the broad learning system (BLS) [40], [41], [42] to enhance its features.”
Self-citationOnline Semisupervised Broad Learning System for Industrial Fault Diagnosis
Pu, X., & Li, C. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3048990 · Cited by 113
A Complex Network-Based Broad Learning System for Detecting Driver Fatigue From EEG Signals
Yang, Y., Gao, Z., Li, Y., Cai, Q., Marwan, N., & Kurths, J. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2956022 · Cited by 112
“We test the performances of three different strategies, namely, the increment of enhancement nodes, the increment of both enhancement and feature nodes, and the increment of input patterns [26].”
BackgroundMethodInfluentialDeep Learning for Remote Sensing Image Scene Classification: A Review and Meta-Analysis
Thapa, A., Horanont, T., Neupane, B., & Aryal, J. (2023) · Remote Sensing · doi:10.3390/rs15194804 · Cited by 132
“Dong et al. [80] integrated a Deep Convolutional Neural Network (DCNN) with Broad Learning System (BLS) [81] for the first time in the remote sensing scene classification domain to extract shallow features and named it FDPResNet.”
BackgroundMultiview High Dynamic Range Image Synthesis Using Fuzzy Broad Learning System
Guo, H., Sheng, B., Li, P., & Chen, C. L. P. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2934823 · Cited by 106
“We use an improved least square to obtain the connecting weight W with smallest training errors, and λ denote the further constraints on the sum of the squared weights in [59].”
BackgroundMethodSelf-citationMFRFNN: Multi-Functional Recurrent Fuzzy Neural Network for Chaotic Time Series Prediction
Nasiri, H., & Ebadzadeh, M. M. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.08.032 · Cited by 106
GreenSea: Visual Soccer Analysis Using Broad Learning System
Sheng, B., Li, P., Zhang, Y., Mao, L., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2988792 · Cited by 106
“First, we use the broad learning system (BLS) [6]–[9].”
MethodSelf-citationChen, H., Chen, Z., Chai, Z., Jiang, B., & Huang, B. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3060766 · Cited by 104
“By integrating CCA into the broad learning framework [17], Chen and Liu [20] have proposed a fast FD strategy where the correlation among measurement signals is regarded as an important feature.”
BackgroundA Survey on Siamese Network: Methodologies, Applications, and Opportunities
Li, Y., Chen, C. L. P., & Zhang, T. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3207112 · Cited by 129
“Liuetal.”
BackgroundInfluentialSelf-citationHierarchical Lifelong Learning by Sharing Representations and Integrating Hypothesis
Zhang, T., Su, G., Qing, C., Xu, X., Cai, B., & Xing, X. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2884996 · Cited by 102
Emotion Classification Using EEG Brain Signals and the Broad Learning System
Issa, S., Peng, Q., & You, X. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2969686 · Cited by 104
“The formula of the establishment of the enhancement nodes after grouping the first n feature maps is presented in (7), and (8) denotes the first m groups of the enhancement nodes [13]”
BackgroundMethodInfluentialOptic Disk and Cup Segmentation Through Fuzzy Broad Learning System for Glaucoma Screening
Ali, R., Sheng, B., Li, P., Chen, Y., Li, H., Yang, P., Jung, Y., Kim, J., & Chen, C. L. P. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3000204 · Cited by 97
“An enhanced least square method is used here to get W with smaller errors, and λ represents the additional restraints on the summation of squares of weights in [15].”
MethodSelf-citationZhang, T., Lei, C., Zhang, Z., Meng, X.-B., & Chen, C. L. P. (2021) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2021.3061466 · Cited by 110
Self-citationHan, S., Zhu, K., Zhou, M., & Cai, X. (2022) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2022.3171549 · Cited by 97
Broad learning system: A new learning paradigm and system without going deep
Chen, C. L. P., & Liu, Z. (2017) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac.2017.7967609 · Cited by 109
Self-citationChen, J., & Qiao, H. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.2966818 · Cited by 96
Sui, S., Chen, C. L. P., Tong, S., & Feng, S. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2947844 · Cited by 92
“Since then, researchers have studied many finite time control design methods based on Lyapunov functions for uncertain systems, and have achieved a series of important results [32], [33], which contributes to the development of research in this control field.”
BackgroundSelf-citationZhang, T., Li, Y., & Chen, C. L. P. (2020) · Information Sciences · doi:10.1016/j.ins.2020.12.021 · Cited by 103
Self-citationCao, B., Zhao, J., Liu, X., Arabas, J., Tanveer, M., Singh, A. K., & Lv, Z. (2022) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2022.3141761 · Cited by 97
“In both the ELM and BLS, the parameters for feature mapping can be randomly determined and not optimized.”
MethodInfluentialRandom-Forest-Bagging Broad Learning System With Applications for COVID-19 Pandemic
Zhan, C., Zheng, Y., Zhang, H., & Wen, Q. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3066575 · Cited by 96
“Drawing on the idea of the random vector function link neural network (RVFLNN), Chen and Liu [42] proposed a”
BackgroundMethodInfluentialBLS-Location: A Wireless Fingerprint Localization Algorithm Based on Broad Learning
Zhu, X., Qiu, T., Qu, W., Zhou, X., Atiquzzaman, M., & Wu, D. O. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3073005 · Cited by 98
“The most important is that the BLS can still achieve less training time for large scale data sets (readers can refer to [27]), it means that the proposed localization algorithm can be applied for large indoor scenarios, such as terminal building and underground parking.”
BackgroundMethodInfluentialConcept-Cognitive Learning Model for Incremental Concept Learning
Shi, Y., Mi, Y., Li, J., & Liu, W. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2882090 · Cited by 91
IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection
Liu, L., Kuang, Z., Chen, Y., Xue, J.-H., Yang, W., & Zhang, W. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3002583 · Cited by 90
“Broad learning system (BLS) [36], [37] develops incremental learning algorithms for increment of input variables [38], feature nodes [39] and enhancement nodes.”
BackgroundIs there a role for statistics in artificial intelligence?
Friedrich, S., Antes, G., Behr, S., Binder, H., Brannath, W., Dumpert, F., Ickstadt, K., Kestler, H. A., Lederer, J., Leitgöb, H., et al. (2021) · Advances in Data Analysis and Classification · doi:10.1007/s11634-021-00455-6 · Cited by 115
Hyperspectral Imagery Classification Based on Semi-Supervised Broad Learning System
Kong, Y., Wang, X., Cheng, Y., & Chen, C. L. P. (2018) · Remote Sensing · doi:10.3390/rs10050685 · Cited by 89
“Surface Object SVM [6] ELM [8] SPELM [9] SSG [23] CNN-PPF [16] BASS-Net [17] R-VCANet [19] HiFi-We [29] BLS [20] SBLS”
BackgroundMethodSelf-citationFan, X.-N., & Zhang, S. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.08.084 · Cited by 94
On the Accuracy–Complexity Tradeoff of Fuzzy Broad Learning System
Feng, S., Chen, C. L. P., Xu, L., & Liu, Z. (2020) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2020.3009757 · Cited by 88
Self-citationYu, W., Zhao, C., & Huang, B. (2020) · Journal of Process Control · doi:10.1016/j.jprocont.2020.06.013 · Cited by 88
Federated Continuous Learning With Broad Network Architecture
Le, J., Lei, X., Mu, N., Zhang, H., Zeng, K., & Liao, X. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3090260 · Cited by 101
“incremental learning without the need for the deep architecture [6].”
BackgroundMethodNiu, B., Duan, P., Li, J., & Li, X. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2894745 · Cited by 90
“Among of these design schemes, several adaptive neural networks (NNs) or fuzzy controller design schemes have been proposed when existing the completely unknown nonlinearities in the nonlinear lower triangular systems [21]–[34].”
BackgroundADP-Based Robust Tracking Control for a Class of Nonlinear Systems With Unmatched Uncertainties
Mu, C., Zhang, Y., Gao, Z., & Sun, C. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2895692 · Cited by 86
Pattern Classification With Corrupted Labeling via Robust Broad Learning System
Jin, J., Li, Y., & Chen, C. L. P. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3049540 · Cited by 89
“Broad Learning System (BLS) [15] was proposed and drawn substantial attention in many research fields, such as text classification [16], time series prediction [17], [18], smart transportation [19].”
Self-citationMulti-agent broad reinforcement learning for intelligent traffic light control
Zhu, R., Li, L., Wu, S., Lv, P., Li, Y., & Xu, M. (2022) · Information Sciences · doi:10.1016/j.ins.2022.11.062 · Cited by 93
Yan, J. J., Guan, X., Yang, X., Chen, C., & Luo, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3525482 · Cited by 86
“Of note, the BLS was first proposed by Chen and Liu [152] in 2018, wherein the incremental learning schemes are conducted for fast remodeling and parameter tuning.”
Self-citationA Learning-Based Framework for Error Compensation in 3D Printing
Shen, Z., Shang, X., Zhao, M., Dong, X., Xiong, G., & Wang, F. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2898553 · Cited by 86
“Very recently, a broad learning system (BLS) has been proposed [37].”
Adaptive Deep Cascade Broad Learning System and Its Application in Image Denoising
Ye, H., Li, H., & Chen, C. L. P. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2978500 · Cited by 91
“Nevertheless, BLS may encounter a slight loss of accuracy compared with deep-learning methods [29].”
BackgroundMethodInfluentialSelf-citationShen, H., Li, F., Cao, J., Wu, Z., & Lü, G. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2959908 · Cited by 84
“Although NCSs have such advantages, some inherent network-induced phenomena in NCSs cannot be avoided [23]–[25].”
BackgroundZou, L., Yu, X., Li, M., Lei, M., & Yu, H. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2988169 · Cited by 84
“To the best of our knowledge, no prior work has employed lasso regularization to optimize the model structure for BL [33], [34].”
BackgroundMethodHybrid Transfer Learning and Broad Learning System for Wearing Mask Detection in the COVID-19 Era
Wang, B., Zhao, Y. J., & Chen, C. L. P. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3069844 · Cited by 97
“Given an input image, the wearing mask regions will be labeled in the output image by the developed deep transfer learning model [9], [10] and the broad learning system (BLS) [11], [12].”
MethodSelf-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.