Design optimization by functional neural networks
Xiyu Liu, Huichuan Duan, Ming Xi Tang · 2005
This paper presents a new design optimization technique by artificial neural networks. Based on the theory of partial ordering and cones in Banach spaces, a new kind of neural networks with functional links is proposed. Learning algorithm lies heavily on the ordering structure of the sample space with an alternative feed-forward and backpropagation technique. Experiments are described with comparison with traditional functional link networks and wavelet networks.