Quantum approximate optimization algorithm for Bayesian network structure learning
Authors: V.P. Soloviev, C. Bielza, P. Larrañaga. Full article: Quantum Information Processing
Untrained graph neural network architectures for denoising signals with irregular supports
Authors: S. Rey, R. Heckel, S. Segarra, and A. G. Marques. Full article: IEEE Trans. Signal Process
Antonio G. Marqués participates in multiple talks worldwide
Professor Antonio G. Marqués has participated as speaker and guest in multiple talks around the world, including: General Chair de Learning on Graphs Madrid Meetup, Madrid, Spain, Nov. 27-29, 2023. Technical Chair de European Signal Process. Conference, Helsinki, Finland, Sep. 4-9, 2023. Speaker in IEEE Intl. Wrksp. on Computational Advances in Multi-Sensor Adaptive Processing, Los […]
Unsupervised learning of global factors in deep generative models
Authors: Peis, I., Olmos, P. M., & Artés-Rodríguez, A. Full article: Pattern Recognition
Multi-source change-point detection over local observation models
Authors: Romero-Medrano, L., & Artés-Rodríguez, A. Full article: Pattern Recognition
Optimal Thresholds for Fracton Codes and Random Spin Models with Subsystem Symmetry
Authors: H. Song , J. Schönmeier-Kromer, K. Liu, O. Viyuela, L. Pollet, and M. A. Martin-Delgado. Full article: American Physical Society
One-Week Suicide Risk Prediction Using Real-Time Smartphone Monitoring: Prospective Cohort Study
Authors: Barrigon ML, Romero-Medrano L, Moreno-Muñoz P, Porras-Segovia A, Lopez-Castroman J, Courtet P, Artés-Rodríguez A, Baca-Garcia E. Full article: J Med Internet Res
Deep autoregressive models with spectral attention
Authors: Moreno-Pino, F., Olmos, P. M., & Artés-Rodríguez, A. Full article: Pattern Recognition
Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classification
Authors: J. Maroñas, D. Hernández-Lobato. Full article: International Conference on Machine Learning
SNUG: Self-Supervised Neural Dynamic Garments
Hyped to share our CVPR 2022 (Oral) paper “SNUG: Self-Supervised Neural Dynamic Garments”. The 3D garment deformations in this clip are learned with a neural network *without* using any dataset of 3D meshes or images🤯The trick? Physics!
