Dynamics of multi-point singular fifth-order Lane-Emden system with
neuro-evolution heuristics
Abstract
Aim of the presented study is to investigate the numerical solution of
fifth-order nonlinear Lane-Emden (LE) based singular system at the
origin with different shape factors developed on the analogous pattern
of standard second order LE equations. The stochastic neuro-evolution
computing is exploited for numerical outcomes by using the artificial
neural networks (ANNs) for applicable mapping and learning of decision
variables with integrated meta-heuristics of genetic algorithms (GAs)
for global search aided with the rapid local search of active-set (AS)
i.e., ANN-GA-AS algorithm. The designed numerical computing approach
ANN-GA-AS implemented effectively for solving fifth-order nonlinear LE
singular system and results of statistical assessments further
authenticate the accuracy, convergence, and stability.