Introduction to Python (optional pre-tutorial) Room: SR4

Introduction to numPy (optional pre-tutorial) Room: SR4

Welcome

• Isabell-A. Melzer-Pellmann (DESY)

Room: SR4

Introduction to Machine Learning (part I)

• Fedor Ratnikov

Room: SR4

Introduction to Machine Learning (part II) Room: SR4

TMVA Tutorial

• Lorenzo Moneta

Room: SR4

Introduction to Deep Learning (part I)

• Dirk Kruecker (DESY)

Room: SR4

Introduction to deep learning + pyTorch tutorial (part II)

• Dirk Kruecker (DESY)

Room: SR4

Introduction to Deep Learning + pyTorch tutorial (part III)

• Dirk Kruecker (DESY)

Room: SR4

Introduction to Deep Learning + pyTorch tutorial (part IV)

• Dirk Kruecker (DESY)

Room: SR4

Deep Learning - Convolutional and recurrent networks

• Gregor Kasieczka (Institut fuer Experimentalphysik / UHH)

Room: SR4

Adversarial Frameworks - from traditional GANs to WGANs and progressive GANs

• Jonas Glombitza (RWTH Aachen)

Room: SR4

Tutorial: Tensorflow

• Adam Elwood (DESY)

Room: SR4

Tutorial: Keras

• Christian Contreras Campana (DESY)

Room: SR4

Networked data-science for research, academic communities and beyond

• Andrey Ustyuzhanin

Room: SR4 There is an exceptional way of doing data-driven research employing networked community. The following examples can illustrate the approach: Galaxy Zoo or Tim Gower’s blog. However many cases of collaboration with the data-science community within competitions organised on Kaggle or Coda Lab platforms usually get limited by restrictions on those platforms. Common Machine Learning quality metrics do not necessarily correspond to the original research goal. Constraints imposed by the problem statement typically look artificial for ML-community. Preparing a perfect competition takes a considerable amount of efforts. On the contrary research process requires a lot of flexibility and ability to look at the problem from different angles. I’ll describe the alternative research collaboration process can bridge the gap between domain-specific research and data science community. Notably, it can involve academic researchers, younger practitioners and all enthusiasts who are willing to contribute. Such research process can be supported by an open computational platform that will be described along with essential examples for the audience of the workshop.

Machine learning outside HEP

• Simone Frintrop

Room: SR4

Machine Learning with Less or no Simulation Dependence

• Benjamin Nachman

Room: SR4

Challenge

• Gregor Kasieczka (Institut fuer Experimentalphysik / UHH)
• Lydia Brenner (DESY)

Room: SR4

Challenge (continued) Room: SR4

Advanced Deep Learning: Understanding the black box, physics, ...

• Gregor Kasieczka (Institut fuer Experimentalphysik / UHH)

Room: SR4

Presentation of the best three challenge results Room: SR4

Likelihood-free inference, its connections with a typical analysis and recent developments in ML

• Gilles Louppe

Room: SR4

Goodbye Room: SR4