Jo. Moody et Pj. Antsaklis, THE DEPENDENCE IDENTIFICATION NEURAL-NETWORK CONSTRUCTION ALGORITHM, IEEE transactions on neural networks, 7(1), 1996, pp. 3-15
An algorithm for constructing and training multilayer neural networks,
dependence identification, is presented in this paper. Its distinctiv
e features are that i) it transforms the training problem into a set o
f quadratic optimization problems that are solved by a number of linea
r equations, ii) it constructs an appropriate network to meet the trai
ning specifications, and iii) the resulting network architecture and w
eights can be further refined with standard training algorithms, like
backpropagation, giving a significant speedup in the development time
of the neural network and decreasing the amount of trial and error usu
ally associated with network development.