Supervised Neural Network Procedures for the Novel Fractional Food Supply Model

This work presents the numerical performances of fractional kind food supply (FKFS) model. The kinds derivatives have been used to acquire accurate and realistic solutions FKFS FKFSM system contains three types, special predator L(x), top-predator M(x) prey populations N(x). different cases model are provided through stochastic procedures scaled conjugate gradient neural networks (SCGNNs). data selection for is chosen as 82%, training 9% both testing authorization. precision designed SCGNNs achieved Adam solutions. To rationality, competence, constancy, correctness approved by using along with simulations regression actions, mean square error, correlation performances, error histograms values state transition measures.