Order estimation in affine state-space neural networks

P. Gil, J. Henriques, A. Dourado, H. Duarte-Ramos
Proceedings of the 2005 IEEE Midnight-Summer Workshop on Soft Computing in Industrial Applications, 2005. SMCia/05.  
The problem of order evaluation for an affine statespace neural network or equivalently the estimation of the number of neurons to be inserted in the hidden layer in a recurrent neural network is here addressed. The proposed method is based on a singular value decomposition applied to an oblique subspace projection given as the projection of the row space of future outputs into the past inputs-outputs row space, along the future inputs row space.
doi:10.1109/smcia.2005.1466961 fatcat:wlh6toqog5ej5itrhr5pip5koe