MINOAS – Machine Intelligence for iNverse imaging, Observation Analysis and Sensing Workshop

Description

Data driven methods have profoundly transformed the fields signal sensing and analysis.

• Machine learning for inverse imaging problems
• Physics-informed and hybrid AI models for inverse problems
• Data-driven priors and generative models in imaging
• Bayesian inference and uncertainty quantification in inverse problems

Call for papers and submission guidelines

Dates: 24-26 September 2025
Location: FORTH, Dougalis room

Registration form

Organizing Committee

• J.L. Starck
• G. Tsagkatakis
• P. Tsakalides

Keynote Speakers

• Prof. David Donoho || Abstract
  Professor of Humanities and Sciences Professor of Statistics Stanford University, USA
  Title: Self-Supervised Learning — Can One Really Do Away with Data Labeling?
• Prof. Yves Wiaux || Abstract
  Head of Laboratory @BASP , Head of Institute @ISSS, Heriot-Watt University, UK
  Title: The R2D2 deep neural network series paradigm for robust ultra-fast precision imaging in radio astronomy
  
• Prof. Maria Vakalopoulou
  Assistant Professor (MCF) CentraleSupelec, University Paris Saclay, leader of the biomathematics group of MICS Laboratory
• Dr. Philippe Ciuciu || Abstract
  CEA Fellow & Research Director (CEA/NeuroSpin and Inria MIND)
  Title: Non-Cartesian MR imaging in the deep learning era
  
• Prof. Mame Diarra FALL || Abstract
  Associate Professor (MCF-HDR) / Mathematics
  Title: Bayesian Image Restoration with Deep Learning-Based Priors
• Prof. Jason McEwen || Abstract
  Professor of Astrostatistics and Astroinformatics University College London, Dept of Space & Climate Physics
  Title: Bayesian Image Restoration with Deep Learning-Based Priors

Important Dates

Registration opens: 1st April 2025
Abstract Submission Deadline: 30th June 2025
Abstract Submission Deadline: 20th July 2025
Notification of acceptance: 25th July 2025
Conference Registration Deadline: 30th August 2025

Registration form