![Ιδρυματικό Αποθετήριο [SANDBOX]](images/dias.logo.png "Ιδρυματικό Αποθετήριο [SANDBOX]"){kind=logo}
Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/61319727-2026-4DE8-B397-F0AC2181F782 | - |
| Αναγνωριστικό | https://doi.org/10.1109/ACCESS.2021.3072973 | - |
| Αναγνωριστικό | https://ieeexplore.ieee.org/document/9402813 | - |
| Γλώσσα | en | - |
| Μέγεθος | 12 pages | en |
| Τίτλος | Rank-R FNN: a tensor-based learning model for high-order data classification | en |
| Δημιουργός | Makantasis Konstantinos | en |
| Δημιουργός | Μακαντασης Κωνσταντινος | el |
| Δημιουργός | Georgogiannis Alexandros | en |
| Δημιουργός | Γεωργογιαννης Αλεξανδρος | el |
| Δημιουργός | Voulodimos, Athanasios | en |
| Δημιουργός | Georgoulas Ioannis | en |
| Δημιουργός | Doulamis, Anastasios | en |
| Δημιουργός | Doulamis, Nikolaos | en |
| Εκδότης | Institute of Electrical and Electronics Engineers | en |
| Περίληψη | An 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 |
| Τύπος | Peer-Reviewed Journal Publication | en |
| Τύπος | Δημοσίευση σε Περιοδικό με Κριτές | el |
| Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
| Ημερομηνία | 2023-03-02 | - |
| Ημερομηνία Δημοσίευσης | 2021 | - |
| Θεματική Κατηγορία | High-order data processing | en |
| Θεματική Κατηγορία | Hyperspectral data classifcation | en |
| Θεματική Κατηγορία | Rank-R FNN | en |
| Θεματική Κατηγορία | Tensor-based neural networks | en |
| Βιβλιογραφική Αναφορά | K. 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 |
Copyright © DIAS 2013
