ACA - towards multi-scale natural density Neuromorphic Computing

"Advanced Computing Architectures (ACA) - towards multi-scale natural-density Neuromorphic Computing” is a pilot project aiming at the specification of a potential future computing architecture for Neuroscience research. The project is funded by the Helmholtz Initiative and Networking Fund for three years and headed by Markus Diesmann. The consortium is composed of five different institutes at the Research Centre Jülich, as well as partner from RWTH Aachen University, the University of Heidelberg, and the University of Manchester.

A central outcome of this pilot project is a comprehensive specification of the Neuroscience applications (models of connectivity, neurons, synapses, plasticity, etc.), and the required computing architectures. The pilot project will moreover develop concepts for hardware implementations with an appropriate balance between flexibility and efficiency which can be realized in a potential long-term interdisciplinary initiative.

INM-6 delivers the neuroscience background for the project as well as the test cases which guide the development of the new neuromorphic architectures. Moreover, INM-6 coordinates theproject.

INM-6 is involved in the following work packages:

WP *Network connectivity and communication*
WP *System definition, integration and operation*
WP *Requirements, validation and benchmarking* (WP leader -> Tom Tetzlaff)
WP *Coordination* (WP leader -> Cordula Huesgen)