E XPLORING HYPER - PARAMETER SPACES OF NEUROSCIENCE MODELS ON HIGH PERFORMANCE COMPUTERS WITH L EARNING TO L EARN Alper Yegenoglu 1,4,* , Anand Subramoney 5 , Thorsten Hater 1 , Cristian Jimenez-Romero 1 , Wouter Klijn 1 , Aaron Pérez Martín 1 , Michiel van der Vlag 1 , Michael Herty 4 , Abigail Morrison 1,2,3 , Sandra Diaz-Pier 1 1 Simulation and Data Lab Neuroscience, Jülich Supercomputing Centre (JSC), Institute for Advanced Simulation, JARA, Forschungszentrum Jülich GmbH, Jülich, Germany 2 Institute of Neuroscience and Medicine (INM-6) and Institute for Advanced Simulation (IAS-6) and JARA BRAIN Institute I, Forschungszentrum Jülich GmbH, Jülich, Germany 3 Computer Science 3 - Software Engineering, RWTH Aachen University, Aachen, Germany 4 Institute of Geometry and Applied Mathematics, Department of Mathematics, RWTH Aachen University, Aachen, Germany 5 Institute of Neural Computation, Ruhr University Bochum, Germany Correspondence: a.yegenoglu@fz-juelich.de ABSTRACT Neuroscience models commonly have a high number of degrees of freedom and only specific regions within the parameter space are able to produce dynamics of interest. This makes the development of tools and strategies to efficiently find these regions of high importance to advance brain research. Exploring the high dimensional parameter space using numerical simulations has been a frequently used technique in the last years in many areas of computational neuroscience. High performance computing (HPC) can provide today a powerful infrastructure to speed up explorations and increase our general understanding of the model’s behavior in reasonable times. Learning to learn is a well known concept in machine learning and a specific method for acquiring constraints to improve learning performance. This concept can be decomposed into a two loop optimization process where the target of optimization can consist of any program such as an artificial neural network, a spiking network, a single cell model or a whole brain simulation. In this work we present L2L as an easy to use and flexible framework to perform hyper-parameter space exploration of neuroscience models on HPC infrastructure. arXiv:2202.13822v1 [cs.NE] 28 Feb 2022