[Smam] FW: Webinar: "Microlocal analysis and deep learning for limited angle tomography", Feb 23rd 2023 at 2:00 PM (CET)

[Liebi Marianne]

In case this is of interest for some of you!
Best regards,
Marianne

From: <tomography-bridge-seminars-request at esrf.fr> on behalf of Nicola VIGANO <nicola.vigano at esrf.fr>
Reply to: "tomography-bridge-seminars at esrf.fr" <tomography-bridge-seminars at esrf.fr>
Date: Friday, 3 February 2023 at 17:17
To: "tomography-bridge-seminars at esrf.fr" <tomography-bridge-seminars at esrf.fr>
Subject: Webinar: "Microlocal analysis and deep learning for limited angle tomography", Feb 23rd 2023 at 2:00 PM (CET)

Dear colleagues,

I would like to invite you to the following webinar. You will receive the ZOOM connection details for the webinar only if you register here:
https://esrf.zoom.us/meeting/register/tJMtcuGsqTwpGtftP4Q9MnVcIRgbnMJocFuR

Cheers,
Nicola
Title: Microlocal analysis and deep learning for limited angle tomography
Speaker: Ozan Öktem (KTH)
February 23rd 2023 at 2:00 pm / 14:00 (CET)

Abstract:
The talk outlines recent progress in developing domain adapted deep neural networks for the task of (a) extracting the wavefront set of an image from its shearlet coefficients and (b) inpainting the invisible part of the wavefront set in limited angle tomography. A key component in both tasks is to represent them as optimal non-randomised decision rules in statistical decision theory. The talk will also outline how to combine these two networks with a deep neural network for reconstruction, whose architecture is obtained by unrolling a suitable iterative scheme. Specifying the visible parts of the wavefront set relies on characterising the microlocal canonical relation of the deep neural network for reconstruction, which here inverts the ray transform. This results in a deep learning based approach for limited angle tomographic reconstruction that is aware of the microlocal canonical relation for the ray transform and also on the characterisation of visible part of the wavefront set.

Bio:
Ozan Oktem is an applied mathematician, specialized in developing theory and algorithms for solving inverse problems.
Inverse problems are often ill-posed, meaning that there can be multiple solutions consistent with data and/or solutions are sensitive to (small) variations in data (instability). Two important examples of Ozan's areas of interest are: The ability to handle the intrinsic instability in ill-posed problems, through a prior model for the model parameter (regularisation), and addressing computational feasibility for large scale inverse problems in time critical applications, like medical imaging.
Much of Ozan's research is therefore in the intersection of mathematical analysis, machine learning, statistics, and numerical analysis.

The link to connect to the webinar will be sent by e-mail.
To receive it, please register for free by clicking here: https://esrf.zoom.us/meeting/register/tJMtcuGsqTwpGtftP4Q9MnVcIRgbnMJocFuR
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.chalmers.se/pipermail/smam/attachments/20230206/52e3d488/attachment.html>