In dealing with complex problems, a monolithic neural network often becomes too large and complex to design and manage. The only practical way is to design modular neural network systems consisting of simple modules. While there has been a lot of work on combining different modules in a modular system in the fields of neural networks, statistics, and machine learning, little work has been done on how to design those modules automatically and how to exploit the interaction between individual module design and module combination. This talk proposes an evolutionary approach to designing modular neural networks. The approach addresses the issue of automatic determination of the number of individual modules and the exploitation of the interaction between individual module design and module combination. The relationship among different modules is considered during the module design. This is quite different from the conventional approach where the module design is separated from the module combination. Experimental results on some benchmark problems are presented and discussed in this talk.