Title :
A hierarchy of hyperbolic macrodynamic equations as a model for network training
Author :
Melnik, Roderick V Nicholas
Author_Institution :
Dept. of Math. & Comput., Southern Queensland Univ., Toowoomba, Qld., Australia
fDate :
29 Jun-4 Jul 1997
Abstract :
The author proposes mathematical models of hyperbolic type for training of neural networks, and its computational implementation using the Markov chain approximation method
Keywords :
Markov processes; feedforward neural nets; hyperbolic equations; learning (artificial intelligence); Markov chain approximation method; computational implementation; hyperbolic macrodynamic equations hierarchy; mathematical models; network training; neural networks; Approximation methods; Australia; Computer networks; Decision making; Equations; Mathematical model; Mathematics; Neural networks; Neurons; Optimal control;
Conference_Titel :
Information Theory. 1997. Proceedings., 1997 IEEE International Symposium on
Conference_Location :
Ulm
Print_ISBN :
0-7803-3956-8
DOI :
10.1109/ISIT.1997.613249
