SPDnet
PulseAugur coverage of SPDnet — every cluster mentioning SPDnet across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New Python library SPD Learn unifies geometric deep learning for neural decoding
A new Python library called SPD Learn has been released, designed to streamline the development and implementation of geometric deep learning models that utilize symmetric positive definite (SPD) matrices. This library …
-
Research paper finds expressivity limits in congruence-based DNNs
A new research paper explores the expressivity limitations of congruence-based neural network architectures when applied to symmetric positive-definite matrices. The study reveals that common semi-orthogonality constrai…
-
FedSPDnet advances federated learning with geometry-aware aggregation strategies
Researchers have developed FedSPDnet, a novel federated learning framework designed for models that process symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. This framework introduces two a…