Frankenstein PSO applied to neural network weights and architectures
Natália Flora De Lima, Teresa B. Ludermir · 2011
In this paper we present the FPSOA-FPSOPa modified version of Frankstein Particle Swarm Optimization (FPSO), which is used to adjust the weights and architectures of a feed forward neural network. To evaluate the algorithm we used benchmark classification problems in medical care area. The results were compared with other algorithms which use the same methodology to find out the weights and architectures.