This title appears in the Scientific Report :
2022
Please use the identifier:
http://hdl.handle.net/2128/33146 in citations.
Optimizing Spiking Neural Networks with L2L on HPC systems
Optimizing Spiking Neural Networks with L2L on HPC systems
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 descri...
Saved in:
Personal Name(s): | Yegenoglu, Alper (Corresponding author) |
---|---|
Contributing Institute: |
Jülich Supercomputing Center; JSC |
Imprint: |
2022
|
Conference: | End of year colloquium 2022 at JSC, Jülich (Germany), 2022-12-08 - 2022-12-08 |
Document Type: |
Talk (non-conference) |
Research Program: |
Helmholtz School for Data Science in Life, Earth and Energy (HDS LEE) Doktorand ohne besondere Förderung Human Brain Project Specific Grant Agreement 3 Human Brain Project Specific Grant Agreement 2 Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups Interactive Computing E-Infrastructure for the Human Brain Project SimLab Neuroscience Center for Simulation and Data Science (CSD) - School for Simulation and Data Science (SSD) |
Link: |
OpenAccess |
Publikationsportal JuSER |
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. |