Hyperbole's blog

Learn notations and algorithms for computing pseudo-gyrodistances, crucial for MLR in Riemannian manifold-based neural networks.

This paper presents novel advancements in SPD neural networks and Grassmann geometry for action recognition and node classification.

GyroSpd++ and Gr-GCN++ outperform baselines in human action recognition and node classification, showing superior accuracy on NTU60, FPHA, and Pubmed datasets.

Explore a novel method for Grassmann logarithmic maps and GCNs, improving graph embeddings and node learning on Grassmann manifolds

Explore how hypergyroplanes and pseudo-gyrodistances revolutionize multinomial logistic regression in structure spaces, adapting it to the Riemannian manifold

Discover how advanced gyrovector space theories are driving innovations in deep neural networks on SPD and Grassmann manifolds.

Leave a Comment