The Dependence Identiication Neural Network Construction Algorithm Interdisciplinary Studies of Intelligent Systems

An algorithm for constructing and training multilayer neural networks, dependence identi cation, 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 and (ii) it constructs an appropriate network to meet the training speci cations. The architecture and network weights produced by the algorithm can also be used as initial conditions for further on-line training by backpropagation or a similar iterative gradient descent training algorithm if necessary. In addition to constructing an appropriate network based on training data, the dependence identi cation algorithm signi cantly speeds up learning in feedforward multilayer neural networks compared to standard backpropagation.