"Inverse Problems in Data Driven Modelling"
In many problems in industry and applied sciences, technological progresses made available small, as well as massive, samples of complex high dimensional data that need to be analyzed and summarized in order to extract relevant information. In this context, learning theory and machine learning provided a suitable framework and effective algorithmic solutions for a variety of problems in computer vision, biomedical informatics, natural language processing and computational neuroscience. Most of these problems are inherently ill-posed. On the other hand, the regularization theory gives powerful tools for solving general inverse and ill-posed problems. In this workshop, we aim at bringing together researchers working on learning, regularization and data modeling problems to present the state of the art in each field, discuss future challenges, and foster fruitful collaborations.
Shuai Lu, Johann Radon Institute, Austria
Sergiy Pereverzyev Jr. (Chair), Johannes Kepler University Linz, Austria
Lorenzo Rosasco, Massachusetts Institute of Technology, USA
Sivananthan Sampath, Johann Radon Institute, Austria
The workshop takes place at the Johann Radon Institute, Hochschulfondsgebäude, Room: HF 9901, July 20-July 23, 2010.
List of Invited Speakers
Conference Guide (pdf)