Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
EN  |  EL

Αναζήτηση

Πλοήγηση

Ο Χώρος μου

Rank-R FNN: a tensor-based learning model for high-order data classification

Makantasis Konstantinos, Georgogiannis Alexandros, Voulodimos, Athanasios, Georgoulas Ioannis, Doulamis, Anastasios, Doulamis, Nikolaos

Απλή Εγγραφή


URIhttp://purl.tuc.gr/dl/dias/61319727-2026-4DE8-B397-F0AC2181F782-
Αναγνωριστικόhttps://doi.org/10.1109/ACCESS.2021.3072973-
Αναγνωριστικόhttps://ieeexplore.ieee.org/document/9402813-
Γλώσσαen-
Μέγεθος12 pagesen
ΤίτλοςRank-R FNN: a tensor-based learning model for high-order data classificationen
ΔημιουργόςMakantasis Konstantinosen
ΔημιουργόςΜακαντασης Κωνσταντινοςel
ΔημιουργόςGeorgogiannis Alexandrosen
ΔημιουργόςΓεωργογιαννης Αλεξανδροςel
ΔημιουργόςVoulodimos, Athanasiosen
ΔημιουργόςGeorgoulas Ioannisen
ΔημιουργόςDoulamis, Anastasiosen
ΔημιουργόςDoulamis, Nikolaosen
ΕκδότηςInstitute of Electrical and Electronics Engineersen
ΠερίληψηAn increasing number of emerging applications in data science and engineering are based on multidimensional and structurally rich data. The irregularities, however, of high-dimensional data often compromise the effectiveness of standard machine learning algorithms. We hereby propose the Rank- R Feedforward Neural Network (FNN), a tensor-based nonlinear learning model that imposes Canonical/Polyadic decomposition on its parameters, thereby offering two core advantages compared to typical machine learning methods. First, it handles inputs as multilinear arrays, bypassing the need for vectorization, and can thus fully exploit the structural information along every data dimension. Moreover, the number of the model's trainable parameters is substantially reduced, making it very efficient for small sample setting problems. We establish the universal approximation and learnability properties of Rank- R FNN, and we validate its performance on real-world hyperspectral datasets. Experimental evaluations show that Rank- R FNN is a computationally inexpensive alternative of ordinary FNN that achieves state-of-the-art performance on higher-order tensor data.en
ΤύποςPeer-Reviewed Journal Publicationen
ΤύποςΔημοσίευση σε Περιοδικό με Κριτέςel
Άδεια Χρήσηςhttp://creativecommons.org/licenses/by/4.0/en
Ημερομηνία2023-03-02-
Ημερομηνία Δημοσίευσης2021-
Θεματική ΚατηγορίαHigh-order data processingen
Θεματική ΚατηγορίαHyperspectral data classifcationen
Θεματική ΚατηγορίαRank-R FNNen
Θεματική ΚατηγορίαTensor-based neural networksen
Βιβλιογραφική ΑναφοράK. Makantasis, A. Georgogiannis, A. Voulodimos, I. Georgoulas, A. Doulamis and N. Doulamis, "Rank-R FNN: a tensor-based learning model for high-order data classification," IEEE Access, vol. 9, pp. 58609-58620, Apr. 2021, doi: 10.1109/ACCESS.2021.3072973.en

Διαθέσιμα αρχεία

Υπηρεσίες

Στατιστικά