A new method in neural network supervised training with imprecision
George D. Magoulas, Michael N. Vrahatis, George Androulakis · 2002
We propose a method that proceeds solely with the minimal information of the error function and gradient which is their algebraic signs and takes minimization steps in each weight direction. This approach seems to be practically useful especially when training is affected by technology imperfections and environmental changes that cause unpredictable deviations of parameter values from the designed configuration. Therefore, it may be difficult or impossible to obtain very precise values for the error function and the gradient of error during training.