Dense deep stochastic configuration network with hybrid training mechanism. (22nd July 2022)

• Record Type: Journal Article
• Authors: Zou, Weidong; Xia, Yuanqing; Cao, Weipeng
• Is Part Of: International journal of computing science and mathematics. Volume 15:Number 3(2022)
• Page Start: 301
• Page End: 314
• Publication Date: 2022-07-22
• Subjects: DSCN -- deep stochastic configuration network -- stochastic configuration network -- randomised neural networks -- randomised algorithms -- neural networks with random weights -- broad learning system -- extreme learning machine -- random vector functional link net -- hybrid training -- generalisation ability; Mathematics -- Periodicals; Computer science -- Periodicals; Mathematics -- Data processing -- Periodicals; 510.285
• Languages: English
• ISSNs: 1752-5055

Abstract

Thanks to the supervised parameter generation strategy and non-iterative training mechanism, deep stochastic configuration network (DSCN) has achieved very efficient modelling efficiency in scenarios with relatively small problem complexity. However, the increasing number of hidden layers and the amount of training data have issued a challenge to the implementation of DSCN. To solve this problem, we propose a Dense DSCN with a Hybrid Training mechanism (HT-DDSCN), which extends the network structure of the DSCN to a dense connection type and combines three typical optimisation techniques and one universal control strategy to optimise the calculation process of the output weights. Extensive experiments on four benchmark regression problems show that HT-DDSCN can significantly improve the generalisation ability and the stability of DSCN.