dc.contributor.author | Polycarpou, Marios M. | en |
dc.contributor.author | Ioannou, Petros A. | en |
dc.contributor.editor | Anon | en |
dc.creator | Polycarpou, Marios M. | en |
dc.creator | Ioannou, Petros A. | en |
dc.date.accessioned | 2019-12-02T10:38:00Z | |
dc.date.available | 2019-12-02T10:38:00Z | |
dc.date.issued | 1992 | |
dc.identifier.isbn | 0-7803-0164-1 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/57555 | |
dc.description.abstract | Summary form only given, as follows. The authors consider the convergence issue that arises in the application of backpropagation algorithms in a special class of neural network architectures, referred to as structured networks, which are used for solving matrix algebra problems. They have developed bounds for the learning rate under which exponential convergence of the training procedure is shown. They also investigated methods for improving the rate of convergence. For a special class of problems, they introduced the orthogonalized backpropagation algorithm, an optimal recursive update law for minimizing a least-squares cost functional, which guarantees exact convergence in one epoch. The results make it possible to obtain valuable insight into neural network learning and to unify certain learning procedures used by connectionists and adaptive control theorists. | en |
dc.publisher | Publ by IEEE | en |
dc.source | Proceedings. IJCNN - International Joint Conference on Neural Networks | en |
dc.source | International Joint Conference on Neural Networks - IJCNN-91-Seattle | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-0026679052&partnerID=40&md5=8e08b654f33c8cbda4c0b726c44d4fae | |
dc.subject | Backpropagation | en |
dc.subject | Control Systems, Adaptive | en |
dc.subject | Learning Systems | en |
dc.subject | Neural Networks | en |
dc.subject | Computer Programming--Algorithms | en |
dc.subject | Mathematical Techniques--Matrix Algebra | en |
dc.title | Convergence analysis for a class of neural networks | en |
dc.type | info:eu-repo/semantics/conferenceObject | |
dc.author.faculty | Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences | |
dc.author.department | Τμήμα Μαθηματικών και Στατιστικής / Department of Mathematics and Statistics | |
dc.type.uhtype | Conference Object | en |
dc.description.notes | <p>Sponsors: IEEE Technical Activities Board Council | en |
dc.description.notes | Int Neural Network Soc | en |
dc.description.notes | Conference code: 16587</p> | en |
dc.contributor.orcid | Ioannou, Petros A. [0000-0001-6981-0704] | |
dc.contributor.orcid | Polycarpou, Marios M. [0000-0001-6495-9171] | |
dc.gnosis.orcid | 0000-0001-6981-0704 | |
dc.gnosis.orcid | 0000-0001-6495-9171 | |