Analysis and Variants of Broad Learning System

Liang Zhang, Jiahao Li, Guoqing Lu, Peiyi Shen, Mohammed Bennamoun, Syed Afaq Ali Shah, Qiguang Miao, Guangming Zhu, Ping Li, Xiaoyuan Lu

Research output: Contribution to journalArticlepeer-review

43 Citations (Scopus)


The broad learning system (BLS) is designed based on the technology of compressed sensing and pseudo-inverse theory, and consists of feature nodes and enhancement nodes, has been proposed recently. Compared with the popular deep learning structures, such as deep neural networks, BLS has the ability of rapid incremental learning and can remodel the system without the usual tedious retraining process. However, given that BLS is still in its infancy, it still needs analysis, improvements, and verification. In this article, we first analyze the principle of fast incremental learning ability of BLS in depth. Second, in order to provide an in-depth analysis of the BLS structure, according to the novel structure design concept of deep neural networks, we present four brand-new BLS variant networks and their incremental realizations. Third, based on our analysis of the effect of feature nodes and enhancement nodes, a new BLS structure with a semantic feature extraction layer has been proposed, which is called SFEBLS. The experimental results show that SFEBLS and its variants can increase the accuracy rate on the NORB dataset 6.18%, Fashion-MNIST dataset by 3.15%, ORL data by 5.00%, street view house number dataset by 12.88%, and CIFAR-10 dataset by 18.42%, respectively, and the four brand-new BLS variant networks also obviously outperform the original BLS.

Original languageEnglish
Pages (from-to)334-344
Number of pages11
JournalIEEE Transactions on Systems, Man, and Cybernetics: Systems
Issue number1
Publication statusPublished - 1 Jan 2022


Dive into the research topics of 'Analysis and Variants of Broad Learning System'. Together they form a unique fingerprint.

Cite this