Asymptotical analysis of a modular neural network
Lincheng Wang, Nasser M. Nasrabadi, S.Z. Der · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
Modular neural networks have been used in several applications because of their superiority over a single neural network in terms of faster learning, proper data representation, and feasibility of hardware implementation. This paper presents an asymptotical performance analysis showing that the performance of a modular neural network is always better than or as good as that of a single neural network when both neural networks are optimized. The minimum mean square error (MSE) that can be achieved by a modular neural network is also obtained.