GANs Tutorial for UZH ML workshop

Tuesday 17 Nov 2020, 16:00 → 18:15 Europe/Zurich

Online

Davide Lancierini (Universitaet Zuerich (CH))

Please register to this event in order to receive all necessary information

General information

This is a workshop tutorial for the UZH ML Workshop [1], it will be given by Davide Lancierini (UZH) and will be held online. It can be followed at the zoom room of the UZH ML Workshop [2] with the password you received via mail.

Abstract

 

Generative Adversarial Networks (GANs) play a key role in the development of fast simulation methods in High Energy Physics. In this workshop we will explore the applications of  GANs  and Conditional GANs to a toy dataset. In particular we will implement common methods to avoid mode collapse phenomena.

The workshop will follow a "code-along" approach with space for discussion on code implementation and performance of GANs in tackling fast simulation problems, thus familiarity with Neural Network model building with Tensoflow and Keras is recommended but not compulsory.

How to participate

Please visit the dedicated github page [3] in order to test the environment and participate to the workshop. 

[1]: https://indico.cern.ch/e/UZHML

[2]: https://uzh.zoom.us/j/91470219654?pwd=Y0JTVHRGa1Ywc2xWTFJlMXE3ek8vdz09

[3]: https://github.com/dlanci/UZHMLWorkshop2020-GAN

16:00 → 16:50 Tutorial - Part 1

Description

Speaker: Davide Lancierini (Universitaet Zuerich (CH))

16:50 → 17:00 Coffee break

17:00 → 18:00 Tutorial - Part 2

Description

Speaker: Davide Lancierini (Universitaet Zuerich (CH))

18:00 → 18:15 Q&A session