Events

Opening Conference of the Einstein Thematic Semester "Varieties, Polyhedra, Computation"

October 7-11, 2019

Speakers include: Daniele Agostini (HU Berlin), Omid Amini (École Polytechnique), Alexander Bobenko (TU Berlin), Felipe Cucker (TU Berlin), Jan Draisma (Universität Bern), Mathias Drton (University of Washington), Michael Joswig (TU Berlin), Kaie Kubjas (Aalto University, Helsinki), Pierre Lairez (INRIA), Laurent Manivel (Paul Sabatier University, Toulouse), Francisco Santos (FU Berlin), Reinhold Schneider (TU Berlin), Rainer Sinn (FU Berlin), Timo de Wolff (Technische Universität Braunschweig)
More information on the homepage: http://ehrhart.math.fu-berlin.de/agplus/school.php


Fall School of the Einstein Thematic Semester "Varieties, Polyhedra, Computation"

September 30- October 4, 2019

Lecturers include: Greg Blekherman (Georgia Tech), Dawei Chen (Boston College), Giorgio Ottaviani (University of Florence), Bernd Sturmfels (MPI Leipzig/Berkeley)
More information on the homepage: http://ehrhart.math.fu-berlin.de/agplus/school.php


BMS Summer School on "Mathematics of Deep Learning"

August 19-30, 2019 at the Zuse Institute Berlin

This summer school is aimed at graduate students in mathematics; postdocs are also encouraged to attend. It will offer lectures on both the theory of deep neural networks, and related questions such as generalization, expressivity, or explainability, as well as on applications of deep neural networks (e.g. to PDEs, inverse problems, or specific real-world problems). Please note that BMS students may register for the summer school by April 8, 2019 by sending an email to summerschool@math-berlin.de.

The first week will be devoted to the theory of deep neural networks, while the second week has a focus on applications. The format is dominated by 1,5 hour lectures by international experts. In addition, there will also be a poster session for the participants.

Our Speakers include: Taco Cohen (Qualcomm), Francois Fleuret (IDIAP | EPF, Lausanne), Eldad Haber (University of British Columbia), Robert Jenssen (Tromso), Andreas Krause (ETH Zurich), Gitta Kutyniok (TU Berlin), Ben Leimkuhler (U Edinburgh), Klaus-Robert Müller (TU Berlin), Frank Noe (FU Berlin), Christof Schütte (FU Berlin | ZIB), Vladimir Spokoiny (HU Berlin | WIAS), Rene Vidal (Johns Hopkins University).




Past Events



8. BIMoS Distinguished Lecture

BIMoS is proud to welcome Carola Schönlieb (Cambridge) as the next BIMoS Distinguished Lecturer. The 8. BIMoS Distinguished Lecture will take place on Wednesday, June 5, 2019 at 6:00 PM s.t.(!) in room H 0106 in the main building of the TU Berlin on the topic of
"From differential equations to deep learning for image processing: How mathematics can help to conserve paintings and trees"
More information can be found on https://www.bimos.tu-berlin.de/menue/bimos_lectures_and_courses/bimos_distinguished_lectures/.


MATH+ Grand Opening

The Cluster of Excellence MATH+ invites you to its official opening on Tuesday, May 14, 2019 from 6.30 PM until 10 PM at the Kosmos Berlin, Karl-Marx-Allee 131a, 10243 Berlin to listen to Prof. Dr. Martin Skutella, spokesperson of MATH+ from the TU Berlin, and Prof. Dr. Günter M. Ziegler, the president of the FU Berlin, and to enjoy a MATH+ Science Slam, a Quiz, and music.
Please register on 8berlin.de/mathplus-grand-opening with the free entrance code: math+go2019 or send an email to events@mathplus.de. More information can be found here.


Kickoff meeting of the ERC project "Deep Learning Theory"

March 27 - 29, 2019 at the Max Planck Institute for Mathematics in the Sciences

Deep Learning is one of the most vibrant areas of contemporary machine learning and one of the most promising approaches to Artificial Intelligence. Deep Learning drives the latest systems for image, text, and audio processing, as well as an increasing number of new technologies. The goal of this project is to advance on key open problems in Deep Learning, specifically regarding the capacity, optimization, and regularization of these algorithms. The idea is to consolidate a theoretical basis that allows us to pin down the inner workings of the present success of Deep Learning and make it more widely applicable, in particular in situations with limited data and challenging problems in reinforcement learning. The approach is based on the geometry of neural networks and exploits innovative mathematics, drawing on information geometry and algebraic statistics. This is a quite timely and unique proposal which holds promise to vastly streamline the progress of Deep Learning into new frontiers.

For more information and registration please visit the conference website: https://www.mis.mpg.de/calendar/conferences/2019/kickoff.html