Title: Dense deep stochastic configuration network with hybrid training mechanism

Authors: Weidong Zou; Yuanqing Xia; Weipeng Cao

Addresses: School of Automation, Beijing Institute of Technology, Beijing, 100081, China ' School of Automation, Beijing Institute of Technology, Beijing, 100081, China ' College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China

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.

Keywords: 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.

DOI: 10.1504/IJCSM.2022.124715

International Journal of Computing Science and Mathematics, 2022 Vol.15 No.3, pp.301 - 314

Received: 25 Jun 2021
Accepted: 14 Aug 2021
Published online: 08 Aug 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article