Data Science & Machine Learning

Europe/Zurich
Room: New York (T-Systems)

Room: New York

T-Systems

T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
Bolliger Christian (ETH Zurich), Valerio Zanetti-Überwasser (T-Systems Schweiz AG)
Description
Introduction

Data Science and Machine Learning have become relevant in many research areas and industries. The amount of collected data repeatedly breaks before known speed and volume barriers, which creates the need for automated data processing. Before automated data processing can take place, a machine or algorithm has to be trained for the intended task, which can be information search/retrieval, gaining insights or taking actions. The training phase might last long and occupy a large part of the available infrastructure. Especially if it has to be repeated on new incoming data. To minimize infrastructure costs, machine learning workloads tend to be offloaded to specialized hardware.

Machines are trained to take semantic action in specific domains. To act successfully in such a context, machine learning can't solely rely on data and general purpose algorithms, domain models play an important role in generating accurate results. Data Science - which can be seen as a combination of mathematics, heuristics and domain knowledge - helps discovering patterns and regularities in data, which ideally give birth to new models that help understanding the digitized ocean.

Key questions
  • What algorithms and computational models are best fit for machine learning at scale?
  • How scalable are the current implementations of support vector machines and deep neuronal networks?
  • Which type of hardware is a good match for offloading machine learning workloads: DSPs, ASICs, GPUs?
  • What deployment models and data flows are most supportive for machine learning applications?
  • How does machine learning impact resource usage in a HPC cluster?
  • What can Data Science adopt from HPC and vice versa?
Participants
  • Alexander Kashev
  • André Kunz
  • Christian Bolliger
  • Christian Gerster
  • Christian Iseli
  • Danuta Paraficz
  • Derek Feichtinger
  • Diana Coman Schmid
  • Douglas Potter
  • Gianfranco Sciacca
  • Hamid Hussain-Khan
  • Hardik Kothari
  • Hayk Sargsyan
  • Ingo Elsen
  • Ivan Usov
  • Jens Zudrop
  • Jiří Kunčar
  • Jonathan Blazek
  • Manuel Kohler
  • MARC GENTILE
  • Marcel Schoengens
  • Mario Jurcevic
  • Martin Jacquot
  • Mattia Belluco
  • Michael Rolli
  • Michele De Lorenzi
  • Nicholas Cardo
  • Nico Färber
  • Norman Del Puppo
  • Olivier Byrde
  • Patrik Burkhalter
  • Ralph Larisch
  • Raluca Hodoroaba
  • Ricardo Silva
  • Riccardo Murri
  • Richard Braendli
  • Roberto Fabbretti
  • Rok Roskar
  • Samuel Fux
  • Sebastian Schubert
  • Sigve Haug
  • Silvan Hostettler
  • Sona Hunanyan
  • Stadler Hans-Christian
  • Steffen Oettich
  • Teodoro Brasacchio
  • Thomas Arter
  • Thomas Wuest
  • Timothée Delubac
  • Tyanko Aleksiev
  • Urban Borštnik
  • Valerio Zanetti-Ueberwasser
    • 9:30 AM
      Coffee and registration Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
    • Welcome and introduction Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
      Conveners: Christian Bolliger (ETH Zurich), Valerio Zanetti-Ueberwasser (T-Systems Schweiz AG)
    • Keynote presentation: Application of Machine Learning Approaches to Real-Time Prediction of Train Arrivals Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten

      The talk will present a solution that T-Systems has created for Deutsche Bahn to improve the passenger information by predicting the arrival of trains in real time based on the trains' current positions.

      It will be shown, how "classical" statistical machine learning approaches can be combined with artificial neural networks to solve the problem. The solution is designed in a way that it can scale horizontally based on an Hadoop based HPC platform. 

      Furtherly, an outlook on new datatypes and compute approaches in industrial HPC applications will be given.

      Convener: Ingo Elsen (T-Systems Schweiz AG)
      slides
    • Keynote presentation: Near Real-Time Optimization of Train Traffic in Densely Used Network Areas at SBB Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten

      SBB operates one of the busiest railway networks in the world. In densely used parts of the railway network the planned headway of 2 minutes between trains requires a strict control of train sequence and train velocity to avoid unnecessary stops and additional delays.

      A near real-time optimization based on mixed integer programming is used to calculate the optimum solution every 6 seconds. This optimization algorithm is an integrated component of the centralized dispatching system of SBB and in operation since 2013.

      Convener: Steffen Oettich (SBB)
    • Big Data tools for Astrophysics Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten

      Astrophysical simulations have been a constant presence on HPC clusters around the world for many years. The computational power is now so large that the biggest production runs can easily generate datasets of hundreds of TB in just a few days. The challenge to efficiently post-process the data is significant, because the data can no longer fit in memory and the usual domain tools very cumbersome to use. To address this problem, and the problem of “big data” analysis on HPC clusters in general, we have undertaken a project to try and bring together the benefits of HPC with the ease-of-use of Big Data frameworks. We have developed an analysis code built on top of Apache Spark to analyze 200+TB outputs from recent state-of-the-art cosmological simulation run on Piz Daint at CSCS. Spark is used for orchestration of work and collection of intermediate results; highly-optimized domain code is used for the main part of the computation. In addition, we have developed a tool that allows for quick and easy deployment and monitoring of Spark clusters on HPC infrastructure. I will discuss the issues inherent in combining scientific codes with Big Data frameworks and the approaches we used to overcome them, from the perspective of both software and hardware.

      Convener: Rok Roskar (ETH Zurich)
      slides
    • 12:15 PM
      Lunch and networking Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
    • Data Science Services at CSCS Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
      Convener: Marcel Schoengens (CSCS)
      slides
    • Analytics on Health Data: Ethical Considerations Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
      Convener: Christian Bolliger (ETH Zurich)
      slides
    • Community Development Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
      Convener: Michele De Lorenzi (CSCS)
    • Transfer to Bombardier Transportation Bus station

      Bus station

      Bombardier Transportation (Switzerland) Ltd Brown Boveri-Strasse 5 8050 Zurich
      picture
    • Welcome @ Bombardier Transportation Toro 1/ K2

      Toro 1/ K2

      Convener: Stéphane Wettstein (Bombardier Transportation)
      slides
    • Condition Monitoring and Condition Based Maintenance on ICN (SBB) and ETR 1000 (Trenitalia) Toro 1/ K2

      Toro 1/ K2

      Bombardier Transportation (Switzerland) Ltd Brown Boveri-Strasse 5 8050 Zurich
      Conveners: Hanspeter Krieger (Bombardier Transportation), Stefano Ritter (Bombardier Transportation)
      picture
    • Hardware and Software Testing for High-Power Traction Systems Room: New York

      Room: New York

      T-Systems

      T-Systems Kloten (Balsberg), Balz-Zimmermann-Strasse 7, CH-8302 Kloten
      Convener: Markus Jörg (Bombardier Transportation)
      picture
    • Farewell and end of the meeting Lab

      Lab