2023/09/14 by Mathieu Seraphim, Seraphim, Mathieu, Alexis Lechervy +7 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Mathematics · #Algorithm #Artificial intelligence #Computer science #Covariance #Engineering #Euclidean distance #Euclidean geometry #FOS: Computer and information sciences #FOS: Electrical engineering #Fractal and DNA sequence analysis #Geometry #Image Retrieval and Classification Techniques #Machine Learning (cs.LG) #Mathematics #Pattern recognition (psychology) #Robotics and Automated Systems #Signal Processing (eess.SP) #Statistics #Transformer #Variety (cybernetics) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2309.07579
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/09/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
In recent years, Transformer-based auto-attention mechanisms have been successfully applied to the analysis of a variety of context-reliant data types, from texts to images and beyond, including data from non-Euclidean geometries. In this paper, we present such a mechanism, designed to classify sequences of Symmetric Positive Definite matrices while preserving their Riemannian geometry throughout the analysis. We apply our method to automatic sleep staging on timeseries of EEG-derived covariance matrices from a standard dataset, obtaining high levels of stage-wise performance.