Summary: In this chapter we describe the basics of Genetic Algorithms (GA) and how they can be used to train artificial neural networks. Supervised training of multilayer perceptrons for classification problems is considered. We also explain how the GA can be hybridized with other algorithms and present two hybrids between it and two classical algorithms for the neural network training: Backpropagation and Levenberg-Marquardt. Several experiments over a set of six applications in the context of bioinformatics are performed comparing the GA, its hybrids, and the classical algorithms mentioned above. The testbed has been chosen from PROBEN1: breast cancer, diabetes, heart disease, gene, soybean, and thyroid. The results show that the genetic algorithm hybridized with Levenberg-Marquardt is a serious competitor for standard approaches.