Order Estimation in Affine State-Space Neural Networks



The problem of order evaluation for an affine state'space 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.


Neural Networks


2005 IEEE Mid-Summer Workshop on Soft Computing in Industrial Applications, June 2005

Cited by

No citations found