Universal Approximation Capability of Broad Learning System and Its Structural Variations

By Ieee C. L. Philip Chen Fellow, Zhulin Liu, Shuang Feng. IEEE Transactions on Neural Networks and Learning Systems, 2019

471 citations recorded by the source corpus.

After a very fast and efficient discriminative broad learning system (BLS) that takes advantage of flatted structure and incremental learning has been developed, here, a mathematical proof of the universal approximation property of BLS is provided. In addition, the framework of several BLS variants with their mathematical modeling is given. The variations include cascade, recurrent, and broad–deep combination structures. From the experimental results, the BLS and its variations outperform several exist learning algorithms on regression performance over function approximation, time series prediction, and face recognition databases. In addition, experiments on the extremely challenging data set, such as MS-Celeb-1M, are given. Compared with other convolutional networks, the effectiveness and efficiency of the variants of BLS are demonstrated.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/8b069be51c20ac10e8ca055a111c981fbbac44d1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wenming Yang
2. Wayne Zhang
3. Zhanghui Kuang
4. Jing-Hao Xue
5. Yimin Chen
6. Liyang Liu

In Computer Vision and Pattern Recognition

1. Wenming Yang
2. Wayne Zhang
3. Zhanghui Kuang
4. Jing-Hao Xue
5. Yimin Chen
6. Liyang Liu

In Control and Systems Engineering

1. Jing-Hao Xue

Citations in the corpus

• Memory-Efficient Class-Incremental Learning for Image Classification (2020, unknown): “RECENT years have witnessed a great development of incremental learning [1]–[19], which has a wide range of real-world applications with the capability of continual model”
• IncDet: In Defense of Elastic Weight Consolidation for Incremental Object Detection (2020, background): “Broad learning system (BLS) [36], [37] develops incremental learning algorithms for increment of input variables [38], feature nodes [39], and enhancement nodes.”