next up previous
Next: References Up: A Modular Neural Previous: Limitations

Conclusion

The usage of a modular architecture consisting of small MLPs to solve real world problems is demonstrated in this paper.

It is shown that for different real world data sets the training is much easier and faster with a modular architecture.

Two different approaches of generalization are combined in this model. It is demonstrated that this results in a generalization advantage on high dimensional input vectors.

Due to the independence of the modules in the input layer parallel training is readily feasible.



Albrecht Schmidt and Zuhair Bandar
Wed Apr 16 13:57:11 MET DST 1997