An objective measure to compare some automatic generation methods of NN architectures
Germán Gutiérrez, José Manuel Molina, Inés María Galván, Araceli Sanchis · 2003
Many methods to codify artificial neural networks have been developed to avoid the defects of direct encoding schema, improving the search into the solution's space. A method to evaluate how the search space is covered and how movement along the search process applying genetic operators is needed in order to evaluate the different encoding strategies for a kind of artificial neural networks, feedforward neural networks. A first step of this method is considered with two encoding strategies, a direct encoding method and an indirect encoding scheme based on cellular automata.