Artificial neural networks design using evolutionary algorithms

Although a great amount of algorithms have been devised to train the weights of a neural network for a fixed topology, most of them are hillclimbing procedures, which usually fall in a local optimum; that is why results obtained depend to a great extent on the learning parameters and the initial weights as well as on the network topology. Evolutionary algorithms have proved to be very effective and robust search methods to locate zones of the search space where finding good solutions, even if this space is large and contains multiple local optimum. This paper intends to be an updated review of the field of design of hybrid EA/ANN methods building on previous reviews such as [1, 2, 3], and also paying special attention to aspects such as variation operators, software and applications.