Design and Analysis of a Hybrid GNN-ZNN Model With a Fuzzy Adaptive Factor for Matrix Inversion

Motivated from the convergence capability achieved by gradient neural network (GNN) and zeroing neural network (ZNN) for matrix inversion, in this article, a novel hybrid GNN-ZNN (H-GNN-ZNN) model is proposed by introducing a fuzzy adaptive control strategy to generate a fuzzy adaptive factor that can change its size adaptively according to the residual error. Due to its fuzzy adaptability, this novel model is called the fuzzy adaptive GNN-ZNN (FA-GNN-ZNN) model for presentation convenience. We prove that the FA-GNN-ZNN model has the better performance than the existing H-GNN-ZNN model under the same conditions. In addition, different activation functions are applied to the FA-GNN-ZNN model to improve its performance further, and the corresponding theoretical analysis is given. Finally, comparative simulation results demonstrate the validity and superiority of the FA-GNN-ZNN model for matrix inversion.

Automated summary

In this article, a novel fuzzy adaptive GNN-ZNN (FA-GNN-ZNN) model is proposed for matrix inversion. By introducing a fuzzy adaptive control strategy, the FA-GNN-ZNN model can adaptively change its size according to the residual error, leading to better performance compared to the existing H-GNN-ZNN model under the same conditions. Additionally, different activation functions are applied to the FA-GNN-ZNN model to further improve its performance, as supported by theoretical analysis and comparative simulation results.