| REPORT DETAIL |
| 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 |
| Scope: |
|
| 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. |
| Comments: |
|
| Languaje: |
|
| Document properties |
| Number of pages: |
9 |
| Size: |
48.72 KB |
| File type: |
pdf (Zipped) |
| Download: |
|
|
|
Departament de Llenguatges i Sistemes Informātics
