A novel design of fractional Meyer wavelet neural networks with application to the nonlinear singular fractional Lane-Emden systems

In this study, a novel stochastic computational frameworks based on fractional Meyer wavelet artificial neural network (FMW-ANN) is designed for nonlinear-singular Lane-Emden (NS-FLE) differential equation. The modeling strength of FMW-ANN used to transformed the NS-FLE system difference equations and approximate theory implemented in mean squared error sense develop merit function equations. Meta-heuristic hybrid computing by exploiting global search efficacy genetic algorithms (GA) supported with local refinements efficient active-set (AS) algorithm optimization design variables FMW-ANN., i.e., FMW-ANN-GASA. proposed FMW-ANN-GASA methodology NS-FLM six different scenarios order exam accuracy, convergence, stability robustness. numerical results are compared exact solutions verify correctness, viability efficacy. statistical observations further validate worth solution singular nonlinear systems.