Stability, Monotonicity, and Necessity Analysis of Gradient Method with Penalty Terms for Dynamic Ridge Polynomial Neural Network
- 13 November 2025
- journal article
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 40 (01)
Abstract
In recent years, high-order neural networks (HONNs) have gained widespread usage due to their excellent approximation ability, incorporating both ∑ neurons and ∏ neurons. The dynamic ridge polynomial neural network (DRPNN), as a type of HONN, has been highly valued. However, during the training process of the DRPNN, slow convergence occurs due to the presence of unknown factors. Given this, we propose a method to enhance the DRPNN convergence speed by incorporating a penalty term into the error function and training it using the gradient method. The proposed method significantly improves the convergence speed during network training. To explain the training characteristics of the proposed method, three theorems, namely stability, monotonicity, and necessity, are theoretically proven. More precisely, the whole network is stable over time based on the ultimate training results. The loss function monotonically decreases. Regarding the necessity, the ultimate training results must be an optimal solution. Furthermore, under the condition of the same iteration steps and error accuracy, experiments concerning function simulation and image simulation are advanced to verify the theoretical effectiveness of the proposed method, with the advanced analysis of the corresponding generalizability being discussed.Keywords
Funding Information
- Special Basic Cooperative Research Programs of Yunnan Provincial Undergraduate Universities Association (202101BA070001-149)
This publication has 33 references indexed in Scilit:
- The novel characteristics for training Ridge Polynomial neural network based on Lagrange multiplierAlexandria Engineering Journal, 2022
- A Lyapunov-stability-based context-layered recurrent pi-sigma neural network for the identification of nonlinear systemsApplied Soft Computing, 2022
- A hybrid sigma-pi neural network for combined intuitionistic fuzzy time series prediction modelNeural Computing and Applications, 2022
- High order fuzzy time series method based on pi-sigma neural networkEngineering Applications of Artificial Intelligence, 2018
- Convergence analysis of BP neural networks via sparse response regularizationApplied Soft Computing, 2017
- Dynamic ridge polynomial neural network with Lyapunov function for time series forecastingApplied Intelligence, 2017
- Elitist teaching–learning-based optimization (ETLBO) with higher-order Jordan Pi-sigma neural network: a comparative performance analysisNeural Computing and Applications, 2016
- An approach to enhance the generalization capability of nonlinear aerodynamic reduced-order modelsAerospace Science and Technology, 2016
- Convergence of gradient method for training ridge polynomial neural networkNeural Computing and Applications, 2012
- Dynamic Ridge Polynomial Neural Network: Forecasting the univariate non-stationary and stationary trading signalsExpert Systems with Applications, 2010