Stability analysis for a recurrent sigma‒pi‒sigma neural network based on a batch gradient algorithm with L2 regularization
Authors:
Open Access
- 3 July 2026
- journal article
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3956
Abstract
Higher-order neural networks (HONNs) have more powerful nonlinear mapping capabilities than traditional feed-forward neural networks do. The recurrent sigma-pi-sigma neural network (RSPSNN), a multilayer higher-order neural network, suffers from slow convergence and poor generalizability when trained using a traditional gradient learning algorithm. To overcome these drawbacks, this work presents a method of accelerating the training of the RSPSNN on the basis of L2 regularization, and the results show that the L2 regularity term can effectively accelerate the convergence of the network during the training process. In addition, we rigorously demonstrate the convergence stability of the proposed algorithm, and the performance of the algorithm is evaluated via classification and approximation experiments, which confirm the theoretical results of this article.Keywords
Funding Information
- Yunnan Provincial Undergraduate Universities Association (202101BA070001-149)
- Yunan Students’ innovation and Entrepreneurship Training Program (S202311393002)
- Yunnan Provincial Department of Education (2025Y1058)
This publication has 39 references indexed in Scilit:
- Effects of input gradient regularization on neural networks time-series forecasting of thermal power systemsComputers & Chemical Engineering, 2024
- Training Sigma-Pi neural networks with the grey wolf optimization algorithmGranular Computing, 2023
- A Fast Adaptive Online Gradient Descent Algorithm in Over-Parameterized Neural NetworksNeural Processing Letters, 2022
- Convergence of Batch Gradient Method for Training of Pi-Sigma Neural Network with Regularizer and Adaptive Momentum TermNeural Processing Letters, 2022
- The novel characteristics for training Ridge Polynomial neural network based on Lagrange multiplierAlexandria Engineering Journal, 2022
- Neural network input feature selection using structured l2 − norm penalizationApplied Intelligence, 2022
- A hybrid sigma-pi neural network for combined intuitionistic fuzzy time series prediction modelNeural Computing and Applications, 2022
- Convergence and gradient algorithm of a class of neural networks based on the polygonal fuzzy numbers representationComplex & Intelligent Systems, 2022
- High order fuzzy time series method based on pi-sigma neural networkEngineering Applications of Artificial Intelligence, 2018
- Convergence of gradient method for training ridge polynomial neural networkNeural Computing and Applications, 2012