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 201–300 of 1,000
A Broad Sparse Fine-Grained Image Classification Model Based on Dictionary Selection Strategy
Zheng, J., Liang, P., Zhao, H., & Deng, W. (2023) · IEEE Transactions on Reliability · doi:10.1109/tr.2023.3309278 · Cited by 46
“Broadlearning system (BLS) [15] consists of feature nodes, enhancement nodes, and output coefficients.”
Broad learning system: Structural extensions on single-layer and multi-layer neural networks
Liu, Z., & Chen, C. L. P. (2017) · International Conference on Security, Pattern Analysis, and Cybernetics (SPAC) · doi:10.1109/spac.2017.8304264 · Cited by 49
“Incremental learning algorithms are discussed and summarised in [11] and [13] which consist of increments of enhancement nodes, feature nodes, and input nodes.”
BackgroundMethodInfluentialSelf-citationHyperspectral Image Clustering Based on Unsupervised Broad Learning
Kong, Y., Cheng, Y., Chen, C. L. P., & Wang, X. (2019) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2019.2907598 · Cited by 46
“More recently, Chen and Liu [7] proposed the broad learning (BL), a three-layer feedforward flat network, which mainly consists of two parts.”
BackgroundMethodSelf-citationXu, Z., Wang, Z., Li, J., Jin, T., Meng, X., & Gao, S. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107536 · Cited by 54
Self-Paced Broad Learning System
Liu, L., Cai, L., Xie, T., & Wang, Y. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3181449 · Cited by 48
“The original BLS [5], WBLS [41], GRBLS [51], as well as CBLS [19] are used for performance comparison.”
BackgroundMethodInfluentialYin, L., & Tao, M. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.120269 · Cited by 46
Ren, Y., Liu, J., Wang, Q., & Zhang, H. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3158697 · Cited by 47
“However, retraining the heterogeneous DA model is labor-intensive and time-consuming [21].”
BackgroundMethodInfluentialA new growing pruning deep learning neural network algorithm (GP-DLNN)
Zemouri, R. M., Omri, N., Fnaiech, F., Noureddine Zerhouni, A., & Fnaiech, N. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04196-8 · Cited by 56
“The state transition mapping can be single-valued or multi-valued [9], and it determines the search strategy to move from one state to another in the state space when the NN grows [40].”
BackgroundLearn#: A Novel incremental learning method for text classification
Shan, G., Xu, S., Li, Y., Jia, S., & Xiang, Y. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113198 · Cited by 49
Batch process fault detection for multi-stage broad learning system
Peng, C., Lu, R., Kang, O., & Wang, K. (2020) · Neural Networks · doi:10.1016/j.neunet.2020.05.031 · Cited by 45
Broad Learning With Reinforcement Learning Signal Feedback: Theory and Applications
Mao, R., Cui, R., & Chen, C. L. P. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3047941 · Cited by 47
Self-citationNeuroscience and Network Dynamics Toward Brain-Inspired Intelligence
Hu, B., Guan, Z., Chen, G., & Chen, C. L. P. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3071110 · Cited by 47
“, in one population) are task-specifically activated to achieve a broad enhancement (panel c) [16], [17].”
BackgroundSelf-citationBagging and Boosting Fine-Tuning for Ensemble Learning
Zhao, C., Peng, R., & Wu, D. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3296685 · Cited by 55
“BF combines LogitBoost [30] and broad learning system (BLS) [31] to achieve higher diversity while maintaining relatively high classification accuracy, leading to better EL performance.”
BackgroundMultiscale BLS-Based Lightweight Prediction Model for Remaining Useful Life of Aero-Engine
Xu, T., Han, G., Zhu, H., Lin, C., & Peng, J. (2024) · IEEE Transactions on Reliability · doi:10.1109/tr.2023.3349201 · Cited by 44
Intuitionistic Fuzzy Broad Learning System: Enhancing Robustness Against Noise and Outliers
Sajid, M., Malik, A. K., & Tanveer, M. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3400898 · Cited by 46
“Here, N denotes the total number of training samples, each of which has dimensions D and C number of classes.”
BackgroundMethodInfluentialHyperspectral Image Classification Based on Domain Adaptation Broad Learning
Wang, H., Wang, X., Chen, C. L. P., & Cheng, Y. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3001198 · Cited by 45
“Then, the MF is randomly mapped to EN for broad expansion and the jth group EN is [30]”
InfluentialSelf-citationHyperspectral image classification based on discriminative locality preserving broad learning system
Chu, Y., Lin, H., Yang, L., Zhang, D., Diao, Y., Fan, X., & Shen, C. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106319 · Cited by 44
Dash, D. R., Dash, P. K., & Bisoi, R. (2021) · Renewable Energy · doi:10.1016/j.renene.2021.04.088 · Cited by 44
Adaptive Broad Learning System for High-Efficiency Fault Diagnosis of Rotating Machinery
Fu, Y., Cao, H., & Chen, X. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3085940 · Cited by 52
“Broad learning system (BLS) [25] provides a feasible way to solve the above-mentioned issues in fault diagnosis.”
BackgroundMethodHan, R., Liu, Z., & Chen, C. L. P. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.108660 · Cited by 46
“Broad Learning System (BLS) model is proposed by Chen et al. [34].”
Self-citationDynamic Moore–Penrose Inversion With Unknown Derivatives: Gradient Neural Network Approach
Zhang, Y., Zhang, J., & Weng, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3171715 · Cited by 43
“Similar to other neural network approaches [25]–[29], nonlinear activation functions, such as the power-sigmoid activation function, powersum activation 2162-237X © 2022 IEEE.”
BackgroundFacial Expression Recognition via Broad Learning System
Zhang, T., Liu, Z., Wang, X., Xing, X., Chen, C. L. P., & Chen, E. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00328 · Cited by 43
“Chen and Liu [26] provide an alternative structure of learning underlying features based on the random vector functional-link neural networks(RVFLNN) [27], [28].”
Self-citationAn ACP-Based Parallel Approach for Color Image Encryption Using Redundant Blocks
Zheng, W., Yan, L., Gou, C., & Wang, F. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3105568 · Cited by 47
Prediction of surface roughness using fuzzy broad learning system based on feature selection
Tian, W., Zhao, F., Sun, Z., Zhang, J., Gong, C., Mei, X., Chen, G., & Wang, H. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.07.012 · Cited by 42
Locating Multiple Equivalent Feature Subsets in Feature Selection for Imbalanced Classification
Han, S., Zhu, K., Zhou, M., Alhumade, H., & Abusorrah, A. M. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3222047 · Cited by 42
“Imbalanced classification aims to reduce the misclassification rate for the samples in a positive class, and the traditional machine learning algorithms, such as support vector machine (SVM) [15], extreme learning machine (ELM) [16] and broad learning system (BLS) [17], are not suitable for solving it since they treat…”
BackgroundKuok, S., & Yuen, K. (2021) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.12663 · Cited by 41
“The 𝑓 th FMG (i.e., 𝐅 𝑓 ) is: where 𝑓 (·) is the 𝑓 th feature of mapping; 𝐡 𝑓 ∈ ℝ 𝑁 𝑓 and 𝐆 𝑓 ∈ ℝ 𝑁 𝑥 ×𝑁 𝑓 are the corresponding randomly generated bias and weight, respectively.”
BackgroundMethodInfluentialA Survey on Masked Facial Detection Methods and Datasets for Fighting Against COVID-19
Wang, B., Zheng, J., & Chen, C. L. P. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3139058 · Cited by 47
“BLS can be as a good selection for classification when training efficiency and small size of model are required in applications.”
BackgroundMethodInfluentialSelf-citationDouble-kernel based class-specific broad learning system for multiclass imbalance learning
Chen, W., Yang, K., Yu, Z., & Zhang, W. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109535 · Cited by 43
Least squares support vector machine with self-organizing multiple kernel learning and sparsity
Liu, C., Tang, L., & Liu, J. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.11.067 · Cited by 43
“In recent years, for large-scale datasets, incremental learning and deep learning have been attracting increasing attention [19-21].”
BackgroundAn efficient model for predicting setting time of cement based on broad learning system
Guo, J., Wang, L., Fan, K., & Yang, B. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106698 · Cited by 41
Xu, Y., Yu, Z., Cao, W., & Chen, C. L. P. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3087517 · Cited by 43
“To automatically extract abstract features, different neural networks have been constructed, such as multilayer perceptron (MLP), extreme learning machine (ELM) [40], and broad learning system (BLS) [41].”
MethodSelf-citationHyperspectral Image Classification Based on Domain Adversarial Broad Adaptation Network
Wang, H., Cheng, Y., Chen, C. L. P., & Wang, X. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3128162 · Cited by 41
“Compared with deep learning, BLS has a simple structure, is easy to combine with other models, and can achieve feature broad expansion [34].”
BackgroundMethodSelf-citationBrain-inspired artificial intelligence research: A review
Wang, G., Bao, H., Liu, Q., Zhou, T., Wu, S., Huang, T., Yu, Z., Lu, C., Gong, Y., Zhang, Z., et al. (2024) · Science China Technological Sciences · doi:10.1007/s11431-024-2732-9 · Cited by 47
“In particular, the architecture discovered in [69,70] could inspire new frameworks of AI models, such as modular deep learning architectures and width learning [71].”
Investigating the Evolution of a Neuroplasticity Network for Learning
Wang, L., & Orchard, J. (2017) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2017.2755066 · Cited by 40
“A broad learning system [8] was proposed to offer an alternative way of learning in deep structure.”
BackgroundData and Knowledge Twin Driven Integration for Large-Scale Device-Free Localization
Zhang, J., Xiao, W., & Li, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3005939 · Cited by 41
“6, different from conventional deep-learning algorithms, BL is an efficient incremental algorithm without the need for deep network architecture [40], [41].”
BackgroundOn Training Traffic Predictors via Broad Learning Structures: A Benchmark Study
Liu, D., Baldi, S., Yu, W., Cao, J., & Huang, W. (2020) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2020.3006124 · Cited by 40
“Let us give a quick overview of BLS, and refer to [25]”
BackgroundMethodAn Adaptive Social Spammer Detection Model With Semi-Supervised Broad Learning
Qiu, T., Liu, X., Zhou, X., Qu, W., Ning, Z., & Chen, C. L. P. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3047857 · Cited by 40
“Broad learning system (BLS) [11] is an effective supervised learning method that builds a high-precision classification model in a short time.”
MethodSelf-citationShi, Q., Hu, M., Suganthan, P. N., & Katuwal, R. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108879 · Cited by 44
Zhang, W., Xu, D., Jiang, B., & Shi, P. J. (2022) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2022.3189221 · Cited by 40
“The concrete stability proof of BLS in dynamic training can be referred in [32] which specifically explains its advantages and effectiveness.”
BackgroundMethodHan, S., Zhu, K., Zhou, M., & Liu, X. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3126711 · Cited by 39
“Note that in BLS [12], three parameters are set to fixed values, that is: 1) regularization one for sparse regularization; 2) shrinkage one for enhancement nodes; and 3) shrinkage one for a sparse autoencoder.”
BackgroundInfluentialXu, X., Bao, S., Liang, P., Qiao, Z., He, C., & Shi, P. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.123124 · Cited by 40
A Comprehensive Study of Learning-based Android Malware Detectors under Challenging Environments
Gao, C., Huang, G., Li, H., Wu, B., Wu, Y., & Yuan, W. (2024) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3597503.3623320 · Cited by 45
“Finally, ALDroid uses the Broad Learning System (BLS) [14] as the classifier for malware detection.”
MethodFeng, S., & Chen, C. L. P. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.073 · Cited by 39
Self-citationLi, Y., Cao, W., Hu, W., & Wu, M. (2020) · Process Safety and Environmental Protection · doi:10.1016/j.psep.2020.02.014 · Cited by 39
Yuan, L., Li, T., Tong, S., Xiao, Y., & Shan, Q. (2021) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2021.3113357 · Cited by 40
Deng, Z., Chan, S. H., Chen, Q., Liu, H., Zhang, L., Zhou, K., Tong, S., & Fu, Z. (2022) · Applied Energy · doi:10.1016/j.apenergy.2022.120385 · Cited by 39
Recent Advances in Fatigue Detection Algorithm Based on EEG
Wang, F., Wan, Y., Li, M., Huang, H., Li, L., Hou, X., Pan, J., Wen, Z., & Li, J. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2023.029698 · Cited by 43
A Survey on Collaborative Learning for Intelligent Autonomous Systems
dos Anjos, J. C. S., Matteussi, K. J., Orlandi, F. C., Barbosa, J. L. V., Silva, J. S., Bittencourt, L. F., & Geyer, C. F. R. (2023) · ACM Computing Surveys · doi:10.1145/3625544 · Cited by 53
“Chen and Liu [9] proposed a Broad Learning System (BLS) to solve these problems and enable reconiguration and fast reconstruction of the network without new training processes.”
BackgroundInfluentialAdaptive Memory Broad Learning System for Unsupervised Time Series Anomaly Detection
Zhong, Z., Yu, Z., Fan, Z., Chen, C. L. P., & Yang, K. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3415621 · Cited by 40
“BLS is a three-layer, flat-structured network characterized by feature nodes, enhancement nodes, and an output layer [27].”
Self-citationThree-way multi-label classification: A review, a framework, and new challenges
Zhang, Y., Zhao, T., Miao, D., & Yao, Y. Y. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.112757 · Cited by 39
Chen, C. L. P., & Feng, S. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2018.2869902 · Cited by 38
“It has been well demonstrated that the performance of conventional neural networks can be greatly improved by incorporating fuzzy theory, and numerous fuzzy-neuro networks [such as: fuzzy RBF networks [12]–[14] and fuzzy BLS [15] based on BLS [16], [17] and fuzzy deep neural network [18]] have been proposed recently w…”
BackgroundSelf-citationDetection of Denial of Service Attacks in Communication Networks
Rios, A. L. G., Li, Z., Bekshentayeva, K., & Trajković, L. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180445 · Cited by 39
Correntropy-based robust extreme learning machine for classification
Ren, Z., & Yang, L. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.100 · Cited by 40
Fu, R., Liang, H., Wang, S., Jia, C., Sun, G., Gao, T., Chen, D., & Wang, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121734 · Cited by 40
Ge, J., Yao, Z., Wu, M., Almeida, J. H. S., Jin, Y., & Sun, D. (2025) · Composites Part B Engineering · doi:10.1016/j.compositesb.2025.112701 · Cited by 40
Cross-Modal Zero-Shot-Learning for Tactile Object Recognition
Liu, H., Sun, F., Fang, B., & Guo, D. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2818184 · Cited by 39
“In fact, the feature descriptors used in broad learning [6] and deep learning [12] can also been seamlessly incorporated into the proposed dictionary learning”
BackgroundMulti-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
Wen, H., Zhang, J., Lin, Q., Yang, K., & Huang, P. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301338 · Cited by 46
“It is noteworthy that such an ensemble structure is naturally apt to parallel implementation and have the potential for incremental learning, e.g., the idea used in broad learning system (Chen and Liu 2018).”
BackgroundUtilizing Two-Phase Processing With FBLS for Single Image Deraining
Lin, X., Ma, L., Sheng, B., Wang, Z.-J., & Chen, W. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2987703 · Cited by 37
“It combines/integrates the Takagi-Sugeno (TS) fuzzy system [53] on basis of broad learning system (BLS) [54].”
MethodA Cascade Broad Neural Network for Concrete Structural Crack Damage Automated Classification
Guo, L., Li, R., & Jiang, B. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3010799 · Cited by 39
“Inspired by the related work of multi-Grained cascade Forest (gcForest) presented by Zhou and Ji [30] and BL system (BLS) proposed by Chen and Liu [29], we propose a CBNN architecture for concrete surface crack damage classification.”
BackgroundMethodInfluentialHu, J. Z., Wu, M., Chen, L., Zhou, K., Zhang, P., & Pedrycz, W. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3035800 · Cited by 37
“Furthermore, the increment of enhancement nodes and feature nodes can be adjusted to improve the performance of BLM, which is detailed in [13].”
BackgroundMethodLearningADD: Machine learning based acoustic defect detection in factory automation
Zhang, T., Ding, B., Zhao, X. W., Liu, G., & Pang, Z. (2021) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2021.04.005 · Cited by 39
Type-2 fuzzy broad learning controller for wastewater treatment process
Han, H., Yang, F., Yang, H., & Wu, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.074 · Cited by 37
LSTM-Based Broad Learning System for Remaining Useful Life Prediction
Wang, X., Huang, T., Zhu, K., & Zhao, X. (2022) · Mathematics · doi:10.3390/math10122066 · Cited by 45
Self-attention random forest for breast cancer image classification
Li, J., Shi, J., Chen, J., Du, Z., & Huang, L. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1043463 · Cited by 40
“In this experiment, firstly, the classification performance of PGLCM-IBL (incremental broad learning) (27) and PGLCM-SARF on breast cancer histopathological images is compared, and secondly, the classification performance of different classification algorithms on breast cancer histopathological images is compared unde…”
MethodMissing-Data Tolerant Hybrid Learning Method for Solar Power Forecasting
Liu, W., Ren, C., & Xu, Y. H. (2022) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2022.3173147 · Cited by 42
Sun, X., Xie, M., Zhou, F., Wu, X., Fu, J., & Liu, J. (2022) · Fuel · doi:10.1016/j.fuel.2022.126531 · Cited by 36
Bai, Y. P., Liu, L., Liu, K., Yu, S., Shen, Y., & Sun, D. (2023) · Building and Environment · doi:10.1016/j.buildenv.2023.111033 · Cited by 41
Stress Severity Detection in College Students Using Emotional Pulse Signals and Deep Learning
Li, M., Li, J., Chen, Y., & Hu, B. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3547753 · Cited by 42
Wu, D., & Mendel, J. M. (2019) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2019.2930022 · Cited by 39
“For example, when the performance of a simple multi-layer perceptron neural network is not enough, more nodes can be added to each hidden layer [8], or enhancement nodes can be added to convert it into a broad learning system [12], [13].”
BackgroundRETRACTED ARTICLE: Facial beauty prediction fusing transfer learning and broad learning system
Gan, J., Xie, X., Zhai, Y., He, G., Mai, C., & Luo, H. (2022) · Soft Computing · doi:10.1007/s00500-022-07563-1 · Cited by 37
RetractedCRNet: A Fast Continual Learning Framework With Random Theory
Li, D., & Zeng, Z. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3262853 · Cited by 46
“Random theory has demonstrated its great potential in fast building neural network models with less computational cost [63], among which RVFLN [17], ELM [19], SCN [21], and BLS [22] are four representatives of random weight neural network family.”
BackgroundMethodInfluentialAn enhanced ensemble deep random vector functional link network for driver fatigue recognition
Li, R., Gao, R., Yuan, L., Suganthan, P. N., Wang, L., & Sourina, O. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106237 · Cited by 39
Evidential Ensemble Preference-Guided Learning Approach for Real-Time Multimode Fault Diagnosis
Liu, Z., Li, C., & He, X. Y. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3332112 · Cited by 35
“In [23], the architecture of the broad learning system (BLS), based on the random vector functional link neural network, is proposed.”
MethodSelf-citationQiu, L., Ma, W., Feng, X., Dai, J., Dong, Y., Duan, J., & Chen, B. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.122719 · Cited by 35
Tang, J., Wang, T., Xia, H., & Cui, C. (2024) · Sustainability · doi:10.3390/su16052042 · Cited by 41
Fault diagnosis of drone motors driven by current signal data with few samples
Chen, G., Li, S., He, Q., Zhou, P., Zhang, Q., Yang, G., & Lv, D. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad3d00 · Cited by 35
“…classification problem, a hybrid neural network with small sample learning capabilities is proposed, leveraging the broad learning system (BLS) [49] and convolutional neural network (CNN) [50] for the analysis of current signal data to address the challenges of small sample fault diagnosis in…”
BackgroundMethodEnsemble Deep Random Vector Functional Link Neural Network Based on Fuzzy Inference System
Sajid, M., Tanveer, M., & Suganthan, P. N. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3411614 · Cited by 40
“3) BLS: Broad learning system [39].”
BackgroundMethodInfluentialChen, L., Huang, Z., Li, Y., Zeng, N., Liu, M., Peng, A., & Jin, L. (2019) · IEEE Access · doi:10.1109/access.2019.2903634 · Cited by 35
Study on a Novel Fault Diagnosis Method Based on VMD and BLM
Zheng, J., Yuan, Y. H., Zou, L., Deng, W., Guo, C., & Zhao, H. (2019) · Symmetry · doi:10.3390/sym11060747 · Cited by 38
“The Broad learning model (BLM) is an effective incremental earning system [78].”
BackgroundMethodInfluentialHan, R., Chen, C. L. P., & Liu, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3040340 · Cited by 35
“Consequently, based on specific image processing, we first design a method named Convolution Feature-based Cascade of Enhancement Nodes BLS (CF-CEBLS) that combines the convolution variation of Broad Learning System (BLS) [26] algorithms to construct the effective diagnosis model of AD.”
MethodSelf-citationImproved deep CNNs based on Nonlinear Hybrid Attention Module for image classification
Guo, N., Gu, K., Qiao, J., & Bi, J. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.01.005 · Cited by 37
A Small Opening Workspace Control Strategy for Redundant Manipulator Based on RCM Method
Guo, K., Su, H., & Yang, C. (2022) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2022.3145645 · Cited by 35
Broad stochastic configuration network for regression
Zhang, C., Ding, S., & Du, W. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108403 · Cited by 35
Growing Echo State Network With an Inverse-Free Weight Update Strategy
Chen, X., Luo, X., Jin, L., Li, S., & Liu, M. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3155901 · Cited by 35
“It should be noted that as a member of the neural network family [27], ESN has some commonality with some other well-developed members, such as zeroing neural networks [28]–[30], broad learning system [31]–[33], and extreme learning machine (ELM) [34].”
BackgroundClass-specific weighted broad learning system for imbalanced heartbeat classification
Fan, W., Si, Y., Yang, W., & Sun, M. (2022) · Information Sciences · doi:10.1016/j.ins.2022.07.074 · Cited by 36
Broad-Learning-Based Localization for Underwater Sensor Networks With Stratification Compensation
Yan, J. J., Yi, M., Yang, X., Luo, X., & Guan, X. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3260192 · Cited by 35
“To figure out this problem, a new concept of learning framework called broad learning (BL) [18], [19] can supply us with an effective answer.”
Broad Graph Convolutional Neural Network and Its Application in Hyperspectral Image Classification
Wang, H., Cheng, Y., Chen, C. L. P., & Wang, X. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3189408 · Cited by 34
“There are total nine classifiers were selected to validate the superiority of our proposed BGCNN: SVM [3], GCN [17], BLS [11], SBLS [12], SSGCN [23], MDGCN [16], SSGAT [20], GCGCN [21], and XBGCN.”
BackgroundMethodSelf-citationAn Overview of Swarm Coordinated Control
Yu, D., Li, J., Wang, Z., & Li, X. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3314581 · Cited by 41
“Fan et al. [131] proposed a new manned/unmanned aerial vehicle (MAV/UAV) collaborative combat network model construction method, combining the index system with complex network.”
MethodMulti-view broad learning system for electricity theft detection
Yang, K., Chen, W., Bi, J., Wang, M., & Luo, F. (2023) · Applied Energy · doi:10.1016/j.apenergy.2023.121914 · Cited by 35
Groupwise Label Enhancement Broad Learning System for Image Classification
Jin, J., Chang, S., Duan, J., Li, Y., Ding, W., Wang, Z., Chen, C. L. P., & Li, P. (2025) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3550175 · Cited by 34
“Broad learning system (BLS) [4] was proposed as a flat randomized neural network that achieves good balance between efficiency and accuracy, eliminating time-consuming parameter adjustments and significantly reducing training time.”
Self-citationA Fast Deep Perception Network for Remote Sensing Scene Classification
Dong, R., Xu, D., Jiao, L., Zhao, J. K., & An, J. (2020) · Remote Sensing · doi:10.3390/rs12040729 · Cited by 35
“A BLS network [22], as exemplified as the purple box in Figure 1, works in three steps: First, the features of the input data mapping are used as the “feature nodes” of the network; second, the features of the mapping are elevated to “enhanced nodes” with randomly generated weights; third, all mapped features and enha…”
BackgroundMethodNeural Networks Based Learning Control for a Piezoelectric Nanopositioning System
Kong, L., Li, D., Zou, J., & He, W. (2020) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.2997801 · Cited by 34
“Then, based on adaptive control [21]–[25] and neural networks [26], [27], adaptive neural network control (ANNC) is proposed and automatically regulates the closed-loop system effectively, which, therefore, has been widely used in control theory and applications [28].”
MethodUnsupervised domain adaptation with self-attention for post-disaster building damage detection
Li, Y., Lin, C., Li, H., Hu, W., Dong, H., & Liu, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.07.005 · Cited by 37
Broad and deep neural network for high-dimensional data representation learning
Feng, Q., Liu, Z., & Chen, C. L. P. (2022) · Information Sciences · doi:10.1016/j.ins.2022.03.058 · Cited by 34
Self-citationLiu, Z., Zhang, Y., Ding, Z., & He, X. Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3222265 · Cited by 36
Self-citationMultiparty Secure Broad Learning System for Privacy Preserving
Cao, X., Wang, C., Lai, J., Huang, Q., & Chen, C. L. P. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3235496 · Cited by 36
Self-citationQian, W., Tu, Y., Huang, J., Shu, W., & Cheung, Y. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3352285 · Cited by 40
Broad learning: A GPU-free image-based malware classification
Vasan, D., Hammoudeh, M. A. A., & Alazab, M. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111401 · Cited by 33
A QoE-Driven Tactile Internet Architecture for Smart City
Wei, X., Duan, Q., & Zhou, L. (2019) · IEEE Network · doi:10.1109/mnet.001.1900078 · Cited by 33
“The BL system, established in the form of a flat neural network, expands the neurons containing feature nodes and enhancement nodes in a broad manner without stacking layers in deep, and calculates the weights by pseudoinverse [15].”
BackgroundProgressive Operational Perceptrons with Memory
Tran, D. T., Serkan Kiranyaz, B., Gabbouj, M., & Iosifidis, A. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.079 · Cited by 36
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.