Title :
The determination of neural network parameters by information theory
Author_Institution :
Frankfurt Univ., Germany
Abstract :
The principle of optimal information distribution is a criterion for the efficient use of the different information storage resources in a given network. Furthermore, it can be used as a tool to balance the system parameters and to obtain the optimal network parameter configuration according to the minimal system storage (system description information) for a given maximal performance error. The principle was derived by maximizing the output information of the network. The use of the principle was demonstrated for the example of a simple nonlinear function approximation
Keywords :
information theory; neural nets; information storage resources; information theory; maximal performance error; minimal system storage; neural network parameters; nonlinear function approximation; optimal information distribution; system parameters; Artificial neural networks; Counting circuits; Entropy; H infinity control; Information theory; Linear approximation; Neural networks; Neurons; Physics; Quantum computing;
Conference_Titel :
Tools for Artificial Intelligence, 1991. TAI '91., Third International Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
0-8186-2300-4
DOI :
10.1109/TAI.1991.167110
