Riemannian batch normalization for SPD neural networks
D Brooks, O Schwander… - Advances in …, 2019 - proceedings.neurips.cc
Covariance matrices have attracted attention for machine learning applications due to their
capacity to capture interesting structure in the data. The main challenge is that one needs to …
capacity to capture interesting structure in the data. The main challenge is that one needs to …
Manifoldnet: A deep neural network for manifold-valued data with applications
Geometric deep learning is a relatively nascent field that has attracted significant attention in
the past few years. This is partly due to the availability of data acquired from non-euclidean …
the past few years. This is partly due to the availability of data acquired from non-euclidean …
[HTML][HTML] Shape-based functional data analysis
Functional data analysis (FDA) is a fast-growing area of research and development in
statistics. While most FDA literature imposes the classical L 2 Hilbert structure on function …
statistics. While most FDA literature imposes the classical L 2 Hilbert structure on function …
Cpr-gcn: Conditional partial-residual graph convolutional network in automated anatomical labeling of coronary arteries
Automated anatomical labeling plays a vital role in coronary artery disease diagnosing
procedure. The main challenge in this problem is the large individual variability inherited in …
procedure. The main challenge in this problem is the large individual variability inherited in …
Fully-connected network on noncompact symmetric space and ridgelet transform based on helgason-fourier analysis
Neural network on Riemannian symmetric space such as hyperbolic space and the manifold
of symmetric positive definite (SPD) matrices is an emerging subject of research in …
of symmetric positive definite (SPD) matrices is an emerging subject of research in …
SBI-DHGR: Skeleton-based intelligent dynamic hand gestures recognition
Hand gesture recognition (HGR) plays a significant role in interpreting the meaning of sign
language, human–computer interaction, and robot control. This paper proposes a real-time …
language, human–computer interaction, and robot control. This paper proposes a real-time …
Building neural networks on matrix manifolds: A Gyrovector space approach
XS Nguyen, S Yang - International Conference on Machine …, 2023 - proceedings.mlr.press
Matrix manifolds, such as manifolds of Symmetric Positive Definite (SPD) matrices and
Grassmann manifolds, appear in many applications. Recently, by applying the theory of …
Grassmann manifolds, appear in many applications. Recently, by applying the theory of …
Vector-valued distance and gyrocalculus on the space of symmetric positive definite matrices
F López, B Pozzetti, S Trettel… - Advances in Neural …, 2021 - proceedings.neurips.cc
We propose the use of the vector-valued distance to compute distances and extract
geometric information from the manifold of symmetric positive definite matrices (SPD), and …
geometric information from the manifold of symmetric positive definite matrices (SPD), and …
Modeling graphs beyond hyperbolic: Graph neural networks in symmetric positive definite matrices
Recent research has shown that alignment between the structure of graph data and the
geometry of an embedding space is crucial for learning high-quality representations of the …
geometry of an embedding space is crucial for learning high-quality representations of the …
A Gyrovector space approach for symmetric positive semi-definite matrix learning
XS Nguyen - European Conference on Computer Vision, 2022 - Springer
Abstract Representation learning with Symmetric Positive Semi-definite (SPSD) matrices
has proven effective in many machine learning problems. Recently, some SPSD neural …
has proven effective in many machine learning problems. Recently, some SPSD neural …