Efficient Moth-Flame-Based Neuroevolution Models

Abstract

This chapter proposes a new efficient moth-flame-embedded multilayer perceptrons (MLP) neuroevolution model to deal with classification problems. Moth-flame optimizer (MFO) is one of the effective swarm-based metaheuristic methods inspired by the natural direction-finding behaviours of moth insects and their well-known entrapment phenomena when they circulate the non-natural lights and flames. MFO is capable of demonstrating a very promising performance in terms of exploration and exploitation inclinations. The proposed MFO-MLP model is extensively substantiated on 16 benchmark datasets, and the results are compared to well-known methods such as particle swarm optimizer (PSO), population-based incremental learning (PBIL), differential evolution (DE), and genetic algorithm (GA). The obtained results indicate the efficacy of the MFO-embedded neuroevolution model as a potential method in dealing with classification cases.