Multiple neural networks coupled with oblique decision trees: a case study on the configuration design of midship structure

The paper is concerning the development of multiple neural networks system of problem domains where the complete input space can be decomposed into several different regions, and these are known prior to training neural networks. The authors adopt an oblique decision tree to represent the divided input space and select an appropriate subnetworks, each of which is trained over a different region of input space. The overall architecture of the multiple neural network system, called the federated architecture, consists of a facilitator, normal subnetworks, and “tile” networks. The role of a facilitator is to choose the subnetwork that is suitable for the given input data using information obtained from decision tree. However, if input data is close enough to the boundaries of regions, there is a large possibility of selecting the invalid subnetwork due to the incorrect prediction of decision tree. When such a situation is encountered, the facilitator selects a “tile” network that is trained closely to the boundaries of a partitioned input space, instead of a normal subnetwork. In this way, it is possible to reduce the large error of neural networks at zones close to borders of regions. Validation of the approach is examined and verified by applying the federated neural network system to the configuration design of a midship structure