Talk (non-conference) (Other)

FZJ-2022-05710

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Optimizing Spiking Neural Networks with L2L on HPC systems

Yegenoglu, A. (Corresponding author)FZJ*

2022

Please use a persistent id in citations: http://hdl.handle.net/2128/33146

Abstract: In my talk I present the optimization of spiking neural networks (SNN) on HPC system using the L2L framework. I explain the problems when training SNNs to learn to solve tasks, then I introduce the concept of learning to learn and the framework L2L which implements the concept. Furthermore, I describe how optimization can be applied with L2L on SNNs and showcase two examples, namely optimizing a spiking reservoir network to classify digits and a swarm with a foraging behaviour.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. HBP SGA2 - Human Brain Project Specific Grant Agreement 2 (785907) (785907)
3. HBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539) (945539)
4. PhD no Grant - Doktorand ohne besondere Förderung (PHD-NO-GRANT-20170405) (PHD-NO-GRANT-20170405)
5. HDS LEE - Helmholtz School for Data Science in Life, Earth and Energy (HDS LEE) (HDS-LEE-20190612) (HDS-LEE-20190612)
6. CSD-SSD - Center for Simulation and Data Science (CSD) - School for Simulation and Data Science (SSD) (CSD-SSD-20190612) (CSD-SSD-20190612)
7. SLNS - SimLab Neuroscience (Helmholtz-SLNS) (Helmholtz-SLNS)
8. ICEI - Interactive Computing E-Infrastructure for the Human Brain Project (800858) (800858)

Appears in the scientific report 2022

---

Database coverage:

---