Differential Evolution-based Neural Network Training Incorporating a Centroid-based Strategy and Dynamic Opposition-based Learning

no code implementations • 29 Jun 2021 • Seyed Jalaleddin Mousavirad, Diego Oliva, Salvador Hinojosa, Gerald Schaefer

This improves exploitation since the new member is obtained based on the best individuals, while the employed DOBL strategy, which uses the opposite of an individual, leads to enhanced exploration.