# Spatio-Temporal RBF Neural Networks

## TL;DR

This paper introduces a spatio-temporal RBF neural network that models nonlinear systems more effectively by separating dynamics and complexities, resulting in faster convergence and lower estimation errors compared to standard methods.

## Contribution

It presents a novel spatio-temporal RBFNN architecture that improves nonlinear system identification by employing time-space orthogonality and separate modeling of dynamics.

## Key findings

- Spatio-temporal RBFNN outperforms standard RBFNNs in convergence speed.
- The proposed method achieves significantly lower estimation errors.
- It is effective for highly nonlinear system modeling.

## Abstract

Herein, we propose a spatio-temporal extension of RBFNN for nonlinear system identification problem. The proposed algorithm employs the concept of time-space orthogonality and separately models the dynamics and nonlinear complexities of the system. The proposed RBF architecture is explored for the estimation of a highly nonlinear system and results are compared with the standard architecture for both the conventional and fractional gradient decent-based learning rules. The spatio-temporal RBF is shown to perform better than the standard and fractional RBFNNs by achieving fast convergence and significantly reduced estimation error.