Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

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

Full record


URI: http://purl.tuc.gr/dl/dias/61319727-2026-4DE8-B397-F0AC2181F782
Year 2021
Type of Item Peer-Reviewed Journal Publication
License
Details
Bibliographic Citation 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. https://doi.org/10.1109/ACCESS.2021.3072973
Appears in Collections

Summary

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.

Available Files

Services

Statistics