SS2.5
RECURSIVE KALMANNET: DEEP LEARNING-AUGMENTED KALMAN FILTERING FOR STATE ESTIMATION WITH CONSISTENT UNCERTAINTY QUANTIFICATION
Hassan Mortada, Cyril Falcon, Yanis Kahil, Mathéo Clavaud, Jean-Philippe Michel, Exail, France
Session:
SS2: Non-deterministic Deep Learning and Uncertainty Quantification Lecture
Track:
Special Sessions
Location:
Utveggio
Presentation Time:
Tue, 9 Sep, 12:10 - 12:30 Italy Time (UTC +2)
Session Chair:
Ercan Kuruoglu, Institute of Data and Information
Presentation
Discussion
Resources
No resources available.
Session SS2
SS2.1: Monte Carlo Functional Regularisation for Continual Learning
Pengcheng Hao, Menghao Zhu, Ercan Kuruoglu, Institute of Data and Information, China
SS2.2: An Uncertainty Quantification Method Based on Evidence theory and Conformal Prediction
Rouaa Hoblos, Noura Dridi, Noureddine Zerhouni, Zeina Al Masry, Femto-st, France
SS2.3: Trustworthy Prediction with Gaussian Process Knowledge Scores
Kurt Butler, The University of Edinburgh, United Kingdom; Guanchao Feng, Tong Chen, Petar Djuric, Stony Brook University, United States
SS2.4: Uncertainty Quantification in Probabilistic Machine Learning Models: Theory, Methods, and Insights
Marzieh Ajirak, Cornell University, United States; Anand Ravishankar, Petar Djuric, Stony Brook University, United States
SS2.5: RECURSIVE KALMANNET: DEEP LEARNING-AUGMENTED KALMAN FILTERING FOR STATE ESTIMATION WITH CONSISTENT UNCERTAINTY QUANTIFICATION
Hassan Mortada, Cyril Falcon, Yanis Kahil, Mathéo Clavaud, Jean-Philippe Michel, Exail, France