Oct 6 – 7, 2021
Europe/Zurich timezone

Recordings from both days are available here: Day1 and Day2


What is brain-inspired neuromorphic computing, and how can combining the unique features of biological neurons with non-von Neumann computing platforms enhance deep learning? Learn how to design and train Spiking Neural Networks through deep and online learning in this two-day tutorial.

About the tutorial:
The tutorial consists of one day of seminars, which will provide a high-level introduction to the emerging field of neuromorphic computing, including:

  • Introduction 
  • An overview of neuromorphic computing 
  • Deep learning with biologically-inspired neural dynamics 
  • Biologically-inspired online learning 
  • Neuromorphic computing in end-end speech recognition 
  • Conclusions and future outlook 

This is then followed by a hands-on tutorial on the second day where participants will learn:

  • Deep learning framework with Spiking Neural Units 
  • Online Spatio-Temporal Learning (OSTL) framework


Thomas Bohnstingl, Angeliki Pantazi, Stanislaw Wozniak
(IBM Research)

About the speakers:

Angeliki Pantazi is a Principal Research Staff Member and manager of the Neuromorphic Computing and I/O Links group at the IBM Research – Zurich in Switzerland. She received her Diploma and Ph.D. degrees in Electrical Engineering and Computer Technology from the University of Patras, Greece. She was named IBM Master Inventor in 2014 and became a senior member of the IEEE in 2015 and a Fellow of IFAC in 2020. She was a co-recipient of the 2009 IEEE Control Systems Technology Award and the 2014 IFAC Industrial Achievement Award. Her current research focuses on neuromorphic computing technologies combined with phase-change memory concepts. She has published over 100 refereed articles and holds over 40 granted patents.

Stanislaw Wozniak is a Research Staff Member at IBM Research - Zurich. He conducts research in the field of neuromorphic computing, taking inspiration from the neural networks in the brain to develop novel computing architectures. He received his Ph.D. in 2017 from École Polytechnique Fédérale de Lausanne. In 2018, he received the Fritz Kutter Award of ETH Zurich and IBM Research Division Award for contributions in neuromorphic computing using phase-change memory devices. His current focus is on closing the gap between the theoretically appealing properties of Spiking Neural Networks and their applications. He has authored more than a dozen publications and contributed to filing of 15 patent applications.

Thomas Bohnstingl is a Predoctoral Researcher at IBM Research – Zurich. He received a master’s degree in computer science as well as in Technical Physics from Graz University of Technology. His current research focuses on the theory of spiking neural networks and efficient implementations thereof on neuromorphic hardware substrates. He has authored several publications and contributed to filing patent applications.


For further questions, e-mail at mpp.tutorials@cern.ch

Local organising committee:
Thea Aarrestad (CERN)
Jennifer Ngadiuba (FNAL)

Maurizio Pierini (CERN)
Vladimir Loncar (CERN)

Sioni P. Summers (CERN)
Jean-Roch Vlimant (Caltech)


IML coordinators:
Pietro Vischia (UCLouvain)
Gian Michele Innocenti (CERN)
Lorenzo Moneta (CERN)
David Rousseau (IJCLab-Orsay)
Simon Akar (UCincinnati)
Riccardo Torre (INFN Genova)
Andrea Wulzer (CERN)

Registration for this event is currently open.
332 / 450