Μια ανασκόπηση της βαθιάς μάθησης: θεωρία, μέθοδοι και εφαρμογές
A review of deep learning: theory, methods & applications
View/
Keywords
Μηχανική μάθηση ; Νευρωνικά δίκτυα ; Αρχιτεκτονική συστήματος ; Αλγόριθμοι ; Βαθιά μάθηση ; Deep learning ; Big data ; Neural networks (Computer science)Abstract
The presented thesis, entitled “A Review of Deep Learning: Theory, Methods & Applications”, is an extensive literature review of deep learning, with regard to the origins and the interdisciplinary nature of the field. Deep learning is a revolutionary machine learning approach, that constitutes a class of machine learning techniques, where many layers of information processing stages in hierarchical supervised architectures are exploited for unsupervised feature learning and for pattern analysis or classification. The origins and the motivations of deep learning are mainly found in artificial neural networks, as well as in other related scientific fields as artificial intelligence, cognitive neuroscience and signal processing among others. In recent years, systems based on deep learning techniques and algorithms have become extremely popular both in academia and in many industry sectors, due to the state of the art performance on numerous machine learning problems. This thesis investigates how the fundamental “deep” ideas have been defined and how research interests have shifted over the years. In this perspective the basic building blocks for building deep learning architectures are presented and analyzed.
Postgraduate Studies Programme
ΠληροφορικήDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα ΠληροφορικήςNumber of pages
102Language
GreekCollections
Except where otherwise noted, this item's license is described as
Attribution-NonCommercial-NoDerivatives 4.0 Διεθνές
Attribution-NonCommercial-NoDerivatives 4.0 Διεθνές