Energy- and size-efficient ultra-fast plasmonic circuits for neuromorphic computing architectures
Energy- and size-efficient ultra-fast plasmonic circuits for neuromorphic computing architectures
Energy- and size-efficient ultra-fast plasmonic circuits for neuromorphic computing architectures

PlasmoniAC (Energy- and Size-Efficient Ultra-Fast Plasmonic Circuits for Neuromorphic Computing Architectures) kick-off meeting was held on January 21st and 22nd, 2020, at the premises of the WinPhos research group from the Aristotle University of Thessaloniki (AUTH) in Thessaloniki, Greece. This European research project, led by AUTH, aims to develop a powerful energy-, size- and cost-efficient neuromorphic platform, blending plasmonics, photonics & nanoelectronics. Following a holistic hardware/software co-design approach, PlasmoniAC’s goal is to release a whole new class of feed-forward and recurrent artificial plasmonic neurons with up to 100 GHz clock frequencies and surpassing the current state-of-the-art energy- and size-efficiencies by 1 and 6 orders of magnitude, embracing them in custom DL training models and addressing real application needs in IT security domain. Representatives of 10 partners of the consortium gathered in Thessaloniki in a highly inspiring atmosphere and successfully launched the project’s activities.