Analysis and Variants of Broad Learning System

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on systems, man, and cybernetics. Systems man, and cybernetics. Systems, 2022-01, Vol.52 (1), p.334-344
Main Authors: Zhang, Liang, Li, Jiahao, Lu, Guoqing, Shen, Peiyi, Bennamoun, Mohammed, Shah, Syed Afaq Ali, Miao, Qiguang, Zhu, Guangming, Li, Ping, Lu, Xiaoyuan
Format: Article
Language:English
Subjects:
Artificial neural networks
Broad learning system (BLS)
Datasets
Deep learning
deep neural network
Feature extraction
four brand-new BLS variant networks
incremental realizations
Learning systems
Machine learning
Neural networks
Nodes
semantic feature extraction layer
Semantics
Sparse matrices
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2168-2216
2168-2232
DOI:10.1109/TSMC.2020.2995205