Title :
Backpropagation of accuracy
Author :
Senashova, M.Yu. ; Gorban, Alexander N. ; Wunsch, Donald C.
Author_Institution :
Krasnoyarsk State Univ., Russia
Abstract :
We solve the problem: how to determine maximal allowable errors, possible for signals and parameters of each element of a network, proceeding from the condition that the vector of output signals of the network should be calculated with given accuracy? “Backpropagation of accuracy” is developed to solve this problem
Keywords :
backpropagation; neural nets; backpropagation of accuracy; maximal allowable errors; output signals; vector; Accuracy; Computational intelligence; Computational modeling; Computer networks; Computer simulation; Electronic mail; Laboratories; Neural networks; Neurons; Region 8;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614206
