Νευρωνικά δίκτυα και αναγνώριση προτύπων
Master Thesis
Date
2011-01-20View/
Subject
Ηλεκτρονικοί υπολογιστές -- Δίκτυα ; Neural networks (Computer science) ; Ηλεκτρονικοί υπολογιστές -- Δίκτυα -- Μέτρα ασφαλείαςAbstract
In recent years neural computing has emerged as a practical technology, with successful applications in many fields. The majorities of these applications is concerned with problems in pattern recognition and make use of feed-forward network architectures such as the multilayer perceptron and the radial basis function network. Also, it has also become widely acknowledged that successful applications of neural computing require a principled, rather than ad hoc, approach. The aim of this Diploma Thesis is to introduce to a treatment of neural networks which reflects these developments. From the perspective of pattern recognition, neural networks can be regarded as an extension of the many conventional techniques which have been developed over several decades. Historically, many concepts in neural computing have been inspired by studies of biological networks. The perspective of statistical pattern recognition, however, offers a much more direct and principled route to many of same concepts.
Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 4.0 Διεθνές
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 4.0 Διεθνές