This paper presents a new compound constructive algorithm of neural networks whereby the fuzzy logic technique is explored as an efficient learning algorithm to implement an optimal network construction from an initial simple 3-layer network while the genetic algorithm is used to help design an improved network by evolutions. Numerical simulations on artificial life demonstrate that compared with the existing network design algorithms such as the constructive algorithms of [1]-[3], the pruning algorithms of[5], [6] and the fixed, static architecture algorithm of [7], the present algorithm, called FuzGa, is efficient in both rime complexity and network performance. The improved time complexity comes from the sufficiently small 3 layer design of neural networks and the genetic algorithm adopted partly because the relatively small number of layers facilitates an utilization of an efficient steepest descent method in narrowing down the solution space of fuzzy logic and partly because trappings into local minima can be avoided by genetic algorithm, contributing to considerable saving in time in the processing of network learning and connection. Compared with 54.8 minutes of MLPs with 65 hidden neurons [7], 63.1 minutes of FlexNet[l] or 96.0 minutes of Pruning[5], our simulation results on artificial life show that the CPU time of the present method reaching the target fitness value of 100 food elements eaten for the present FuzGa has improved to 42.3 minutes by SUN's SPARCstation-10 of SuperSPARC 40MHz machine for example. The role of hidden neurons is elucidated in improving the performance level of the neural networks of the various schemes developed for artificial life applications. The effect of population size on the performance level of the present FuzGa is also elucidated.
