Modular design for neural computing problems

We study the feasibility and the performance of modular design concept in some neural network problems. By decomposing the given soft computing problem into smaller modules, it is shown that comparable performance can be achieved with improvement on computation and design complexity. A survey of typical modular techniques shows large-scale nonlinear problems can alleviate its dimensionality curse with modular technique. A pattern recognition problem for aircraft trajectory prediction using NeuroFuzzy learning with a two stage modular learning design is presented. Decoupled data are used to train respective neural network modules. A genetic algorithm is used to aggregate all the learned modules so that it is ready for online pattern recognition purpose. As compared with the non-modular approach, the modular approach offers comparable prediction performance with significantly lower overall …