Spatio-Temporal RBF Neural Networks
This work addresses system identification for nonlinear systems, but it appears incremental as it extends existing RBF methods with spatio-temporal modeling.
The authors tackled the nonlinear system identification problem by proposing a spatio-temporal extension of RBF neural networks, which achieved fast convergence and significantly reduced estimation error compared to standard and fractional RBFNNs.
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.