.png){kind=icon}
.png){kind=icon}
Return
Graph-based broad learning system for classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.07.065.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Broad learning system (BLS) is viewed as an alternative method of deep neural network (DNN). Comparing with DNN, BLS can reach a similar performance with much faster learning speed. BLS contains two kinds of features: the mapped features and the enhancement nodes. The mapped features are obtained by randomly generated connecting weights and biases which are then fine-tuned by sparse autoencoder. But sparse autoencoder, as an unsupervised leaning algorithm, will lose the information of ground truths. The enhancement nodes are formed based on the mapped features with randomly gen-erated weights and biases. However, this random process cannot guarantee the quality of these formed nodes. It means BLS may be unable to learn useful enough representations of original data. Considering the effectiveness of extreme learning machine based autoencoder (ELM-AE), we first propose a novel graph-based ELM-AE (GBEAE) method. Then, a GBEAE-based broad learning system (GBEAE-BLS) is intro-duced to overcome the disadvantages discussed above. Finally, we use 23 datasets to test the perfor-mance of GBEAE-BLS. Experimental results demonstrate that GBEAE-BLS has evident superiorities on these datasets, comparing with related learning algorithms. (c) 2021 Published by Elsevier B.V.
Keywords:
Broad learning system
Extreme learning machine
Autoencoder
Graph
Classification