The Dependence Identification Neural Network Construction Algorithm
J. O. Moody and P. J. Antsaklis
IEEE Transactions on Neural Networks, Vol 7, No 1, pp. 3-15, January 1996.
Abstract -- An algorithm for constructing and training multi-layer neural networks, dependence identification, is presented in this paper. Its distinctive features are that i) it transforms the training problem into a set of quadratic optimization problems that are solved by a number of linear equations, ii) it constructs an appropriate network to meet the training specifications, and iii) the resulting network architecture and weights 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 usually associated with network development.
Also appeared as Technical Report isis-93-005, Department of Electrical Engineering, University of Notre Dame, Oct. 1993.
[postscript file] [pdf file]