[DPS-seminario] Fwd: Call for Papers - JMIV - Mathematical Foundations of Deep Learning in Imaging Science

[Pablo Musé]

> Begin forwarded message:
> 
> From: Katrina Turner <Katrina.Turner at springernature.com>
> Subject: Call for Papers - JMIV - Mathematical Foundations of Deep Learning in Imaging Science
> Date: August 1, 2018 at 4:21:35 PM GMT-3
> To: "pmuse at fing.edu.uy" <pmuse at fing.edu.uy>
> 
> Dear Researcher:
>  
> The Journal of Mathematical Imaging and Vision would like to announce the opportunity to contribute to an upcoming Special Issue on “MATHEMATICAL FOUNDATIONS OF DEEP LEARNING IN IMAGING SCIENCE.”
>  
> Please see below for details.
>  
>  
> Call for Papers
>  
> Special Issue of the Journal of Mathematical Imaging and Vision (JMIV)
>  
> Mathematical Foundations of
> Deep Learning in Imaging Science
>  
> Guest Editors:
>  
> Joan Bruna          (New York University, USA)
> Eldad Haber        (University of British Columbia, Vancouver, USA)
> Gitta Kutyniok    (TU Berlin, Germany)
> Thomas Pock       (Graz University of Technology, Austria)
> Rene Vidal           (Johns Hopkins University, Baltimore, USA)
>  
>  
> Topics of Interest
>  
> Deep learning methods have become an omnipresent and highly successful part of recent approaches in imaging and vision. However, in most cases they are used on a purely empirical basis without real understanding of their behavior. From a scientific viewpoint, this is unsatisfying.
>  
> Many mathematically inclined researchers have a strong desire to understand the theoretical reasons for the success of these approaches and to find relations between deep learning and mathematically well-established techniques in imaging science. The goal of this special issue is to showcase their latest research results and to promote future research in this direction.
>  
> Topics of interest include, but are not limited to:
>  
> ·         mathematical introspection into the behavior of deep learning methods, e.g. through
> o   theoretical insights into their expressive power, quality, stability, and efficiency
> o   analysis of their ability to handle the curse of dimensionality investigation of their generalization properties
> o   theoretical bounds on their necessary complexity theories for architectural design
> o   characterization of their loss surface analysis of optimization algorithms
> o   mathematical theories for generative adversarial networks
>  
> ·         connections between deep learning and successful mathematical concepts in image analysis such as
> o   radial basis functions, splines, and harmonic analysis
> o   sparsity, compressed sensing, and dictionary learning subspace methods
> o   inverse problems, regularization theory, and operator learning variational methods, optimization, and optimal control ordinary and partial differential equations
> o   information theory, information geometry, and the physics of information
> o   statistical learning theory
>  
> Gaining mathematical insights will be the decisive criterion for inclusion into this special issue. Manuscripts which are primarily experimental are not eligible.
>  
>  
> Deadline and Submission Instructions
>  
> ·         Deadline for submission: November 30, 2018 
>  
> The printed special issue will appear in 2019. We aim at fast and efficient reviewing, starting immediately after paper submission. Since accepted manuscripts will become available directly as online first articles, earlier submission is helpful and encouraged. If an individual manuscript requires substantially more time than the others, it will be published in a regular JMIV issue.
>  
> ·         The usual JMIV submission guidelines apply. All submissions will be peer reviewed according to the JMIV standards. Manuscripts that extend conference papers must contain at least 30 % novel material. There is no page limit.
>  
> ·         Submissions must be uploaded through the regular login site of JMIV:
> http://www.editorialmanager.com/jmiv/default.aspx <http://www.editorialmanager.com/jmiv/default.aspx>
>  
> ·         Please make sure to choose the “Mathematical Foundations of Deep Learning in Imaging Science” Special Issue after logging in to the JMIV editorial manager. This guarantees that your submission will be assigned to the above guest editors.
>  
> Website: http://www.mia.uni-saarland.de/JMIV/si-deep-learning.html <http://www.mia.uni-saarland.de/JMIV/si-deep-learning.html>
>  
> More information: Joachim Weickert (weickert at mia.uni-saarland.de <mailto:weickert at mia.uni-saarland.de>)

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://www.fing.edu.uy/pipermail/dps-seminario/attachments/20180801/636c1490/attachment-0001.html>