Departament de Cičncies de la Computació
Home Spanish  |  English

Id. report:  LSI-09-31-R
Title:  Maximum Tolerance and Maximum Greatest Tolerance
Author(s):  Molinero, X.,  Freixas, J.
Date (year-month-day):  2009-09-23
Document Type: 
Keyword(s):  Neural nets, circuit-switching networks, deterministic and structural
Abstract:  An important consideration when applying neural networks is the sensitivity to weights and threshold in strict separating systems representing a linearly separable function. Two parameters have been introduced to measure the relative errors in weights and threshold of strict separating systems: the tolerance and the greatest tolerance. Given an arbitrary separating system we study which is the equivalent separating system that provides maximum tolerance or/and maximum greatest tolerance.
Document properties 
Number of pages:  9
Size:  48.72 KB
File type:  pdf  (Zipped)