Title :
The dependence identification neural network construction algorithm
Author :
Moody, John O. ; Antsaklis, Panos J.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
An algorithm for constructing and training multilayer neural networks, dependence identification, is presented in this paper. Its distinctive features are that: 1) it transforms the training problem into a set of quadratic optimization problems that are solved by a number of linear equations; and 2) it constructs an appropriate network to meet the training specifications. The architecture and network weights produced by the algorithm can also be used as initial conditions for further online 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 identification algorithm significantly speeds up learning in feedforward multilayer neural networks compared to standard backpropagation
Keywords :
backpropagation; feedforward neural nets; identification; iterative methods; neural net architecture; optimisation; parallel architectures; architecture; backpropagation; dependence identification; iterative gradient descent learning; multilayer neural networks; network weights; neural network construction algorithm; quadratic optimization; training specifications; Backpropagation algorithms; Equations; Feedforward neural networks; Intelligent networks; Iterative algorithms; Multi-layer neural network; Neural networks; Neurons; Pattern matching; Transforms;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.375051
