Engineers are often confronted with the problem of extracting information about poorly known processes from data. Discerning the significant patterns in data, as a first step to process under-standing, can be greatly facilitated by reducing dimensionality. An artificial neural network can develop a compact representation of the input data. The neural network contains an internal "bottleneck" layer and two additional hidden layers. In the case of this type neural network, the inputs of the network are reproduced at the output layer. An important problem is to determine the optimal neural network architecture to acquire the optimal nonlinear feature space map. This paper proposes that information criteria are applied to determine the optimal neural network architecture and presents the superiority of the Neural Network Information Criterion (NNIC) for acquisition of the optimal nonlinear feature space map with a simple simulation.
展开▼
