Universal Approximation Capability of Broad Learning System and Its Structural Variations

Chen, C. L. Philip; Liu, Zhulin; Shuang, Feng

doi:10.1109/tnnls.2018.2866622

Cited by 391 publications

(145 citation statements)

References 26 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…For example, Zhang et al [30] provided evidence about how face recognition with the help of BLS could remain unaffected by the number of facial features with intense illumination and occlusion and meanwhile maintaining a prominent accuracy. Chen et al [31] unraveled the superiority of BLS and its variants to several existing learning algorithms in time series prediction and performance regression on face recognition database. Compared with other classic structures, the efficiency and effectiveness of the BLS variants have been fully testified.…”

Section: Broad Learning Systemmentioning

confidence: 99%

Facial Beauty Prediction via Local Feature Fusion and Broad Learning System

Zhai

Qin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Facial beauty prediction (FBP), as a frontier topic in the domain of artificial intelligence regarding anthropology, has witnessed some good results as deep learning technology progressively develops. However, it is still limited by the complexity of the deep structure network in need of a large number of parameters and high dimensions, easily leading to a great consumption of time. To solve this problem, this paper proposes a fast training FBP method based on local feature fusion and broad learning system (BLS). Firstly, two-dimensional principal component analysis (2DPCA) is employed to reduce the dimension of the local texture image so as to lessen its redundancy. Secondly, local feature fusion method is adopted to extract more advanced features through avoiding the effects from unstable illumination, individual differences, and various postures. Finally, extensional feature eigenvectors are input to the broad learning network to train an efficient FBP model, which effectively shortens operational time and improve its preciseness. Extensive experiments with the proposed method on large scale Asian female beauty database (LSAFBD) can be conducted within 13.33s while sustaining an accuracy of 58.97%, impressively outstripping other state-of-the-art methods in training speed. INDEX TERMS Facial beauty prediction (FBP); local feature fusion; broad learning system (BLS);

show abstract

Section: Broad Learning Systemmentioning

confidence: 99%

Facial Beauty Prediction via Local Feature Fusion and Broad Learning System

Zhai

Qin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In contrast to deep learning that consumes expensive computational cost for network training, the broad learning architecture offers a computationally efficient alternative Chen et al, 2019). In the typical conventional deep learning architecture (Goodfellow et al, 2016;Schmidhuber, 2015), the neural networks are configured with stacks of hierarchical layers and the modification of the architec-ture requires retraining of the entire network.…”

Section: Nonparametric Spatial Modelingmentioning

confidence: 99%

“…Lary, Alavi, Gandomi, and Walker (2016) compared the features of some machine learning techniques and their performance on geosciences problems. Chen, Liu, and Feng (2019) compared four machine learning techniques, including the Bayes' net, radial basis function classifier, logistic model tree, and random forest models, for landslide susceptibility modeling. Nabian and Meidani (2018) presented a deep learning framework for seismic reliability analysis of transportation network.…”

Section: Introductionmentioning

confidence: 99%

“…Nabian and Meidani (2018) presented a deep learning framework for seismic reliability analysis of transportation network. Chen, Liu, and Feng (2019) compared four machine learning techniques, including the Bayes' net, radial basis function classifier, logistic model tree, and random forest models, for landslide susceptibility modeling. Woollam, Rietbrock, Bueno, and De Angelis (2019) applied the convolutional neural network to classify seismic location and severity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Broad learning for nonparametric spatial modeling with application to seismic attenuation

Kuok

Yuen

2019

Computer aided Civil Eng

View full text Add to dashboard Cite

Spatial modeling is a core element in geographical information science. It incorporates geographic information to construct the relationship for interpreting the behavior of spatial phenomena. In this paper, a broad learning framework for nonparametric spatial modeling is presented. Broad learning overcomes the obstacle of expensive computational consumption in deep learning and provides a powerful computationally efficient alternative. In contrast to the deep learning architecture that is configured with stacks of hierarchical layers, broad learning networks are established in a flat manner that can be flexibly reconfigured with the inherited information from the trained network. To develop the broad learning network, a simple prototype network is established as the initial trial and it is modified incrementally to enhance its data fitting capacity. Consequently, complex relationship of unstructured spatial data can be modeled efficiently. To demonstrate the efficacy and applicability of the broad learning framework, we will present a simulated example and a real application using the strong ground motion records on the 2008 great Wenchuan earthquake.

show abstract

“…Also, the structure of this network can be expanded flexibly in a wide sense. Like a deep structure neural network, the approximation capability of an incremental learning network is universal (Chen et al, 2018). Hence, it has been successfully engaged in different fields employing efficient modeling and fast learning ability.…”

Section: Introductionmentioning

confidence: 99%

An Incremental Learning Framework to Enhance Teaching by Demonstration Based on Multimodal Sensor Fusion

Zhong

Yang

et al. 2020

Front. Neurorobot.

View full text Add to dashboard Cite

Though a robot can reproduce the demonstration trajectory from a human demonstrator by teleoperation, there is a certain error between the reproduced trajectory and the desired trajectory. To minimize this error, we propose a multimodal incremental learning framework based on a teleoperation strategy that can enable the robot to reproduce the demonstration task accurately. The multimodal demonstration data are collected from two different kinds of sensors in the demonstration phase. Then, the Kalman filter (KF) and dynamic time warping (DTW) algorithms are used to preprocessing the data for the multiple sensor signals. The KF algorithm is mainly used to fuse sensor data of different modalities, and the DTW algorithm is used to align the data in the same timeline. The preprocessed demonstration data are further trained and learned by the incremental learning network and sent to a Baxter robot for reproducing the task demonstrated by the human. Comparative experiments have been performed to verify the effectiveness of the proposed framework.

show abstract

Universal Approximation Capability of Broad Learning System and Its Structural Variations

Cited by 391 publications

References 26 publications

Facial Beauty Prediction via Local Feature Fusion and Broad Learning System

Facial Beauty Prediction via Local Feature Fusion and Broad Learning System

Broad learning for nonparametric spatial modeling with application to seismic attenuation

An Incremental Learning Framework to Enhance Teaching by Demonstration Based on Multimodal Sensor Fusion

Contact Info

Product

Resources

About