階層型ニューラルネットワークにおけるマルチブランチ構造とその局所性

抄録

Neural networks (NNs) can solve only a simple problem if the network size is too small, on the other hand, if the network size increases, it costs a lot in terms of memory space and calculation time. So, we have studied how to construct the network structure with high performances and low costs in space and time. A solution is a multi-branch structure. Conventional NNs use the single-branch for the connections, while the multi-branch structure has multi-branches between nodes. In this paper, a new method which enables the multi-branch NNs to have localized property is proposed. It is well known that RBF networks have localized property that makes it possible to approximate functions faster than sigmoidal NNs. By using the multi-branch structure having localized property of RBF networks, NNs could obtain high performances keeping the lower costs in space and time. Simulation results of function approximations and a classification problem illustrated the effectiveness of multi-branch NNs.