Number of the records: 1
Learning of Multilayer Perceptrons with Piecewise-Linear Activation Functions
- 1.
SYSNO ASEP 0320845 Document Type K - Proceedings Paper (Czech conf.) R&D Document Type The record was not marked in the RIV Title Learning of Multilayer Perceptrons with Piecewise-Linear Activation Functions Title Učení vícevrstvých perceptronů s po částech lineárními aktivačními funkcemi Author(s) Kozub, P. (CZ)
Holeňa, Martin (UIVT-O) SAI, RIDSource Title MIS 2008. - Praha : Matfyzpress, 2008 / Obdržálek D. ; Štanclová J. ; Plátek M. - ISBN 978-80-7378-076-0
S. 27-46Number of pages 20 s. Action MIS 2008. Malý informatický seminář /25./ Event date 12.01.2008-19.01.2008 VEvent location Josefův důl Country CZ - Czech Republic Event type CST Language eng - English Country CZ - Czech Republic Keywords artificial neural networks ; multilayer perceptrons ; activation functions ; function approximation ; constrained optimization Subject RIV IN - Informatics, Computer Science R&D Projects GA201/08/0802 GA ČR - Czech Science Foundation (CSF) GA201/08/1744 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z10300504 - UIVT-O (2005-2011) Annotation This paper presents an overview of the techniques used to solve constrained optimization problems using evolutionary algorithms. The construction of the fitness function together with the handling of feasible and infeasible individuals is discussed. Approaches using penalty functions, special representations, repair algorithms, methods based on separation of objective and constraints and multiobjective techniques are mentioned. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2009
Number of the records: 1