DIKUL - logo
E-viri
Celotno besedilo
  • Moreira, Orlando; Yousefzadeh, Amirreza; Chersi, Fabian; Cinserin, Gokturk; Zwartenkot, Rik-Jan; Kapoor, Ajay; Qiao, Peng; Kievits, Peter; Khoei, Mina; Rouillard, Louis; Ferouge, Aimee; Tapson, Jonathan; Visweswara, Ashoka

    2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020-March
    Conference Proceeding

    Neuronflow is a neuromorphic, many core, data flow architecture that exploits brain-inspired concepts to deliver a scalable event-based processing engine for neuron networks in Live AI applications. Its design is inspired by brain biology, but not necessarily biologically plausible. The main design goal is the exploitation of sparsity to dramatically reduce latency and power consumption as required by sensor processing at the Edge.