We propose a new Riemannian-based deep learning network to generate more discriminative features for electroencephalogram (EEG) classification. Our key innovation lies in learning the Riemannian barycenter for each class within a Riemannian geometric space. The proposed model normalizes the distribution of SPD matrices and learns the center of each class to penalize the distances between the matrix and the corresponding class centers. As a result, our framework can further simultaneously reduce the intra-class distances, and enlarge the inter-class distances for the learned features.
Related publications
1. Deep Riemannian Barycenter Network with SPD matrices in EEG Classification, in preparation
2. B Kim, Y Suh, H Lee, S Jo, Nonlinear Ranking Loss on Riemannian Potato Embedding, International Conference on Pattern Recognition (ICPR) 2020 [LINK] [PDF]
