CEA-Leti: Neuromorphic Device Uses Up to ‘5 Orders of Magnitude’ Less Energy
by staff from High-Performance Computing News Analysis | insideHPC on (#615T3)
GRENOBLE, France - July 7, 2022 - Technical research institute CEA-Leti announced it has developed an event-driven, object-localization system that couples piezoelectric, ultrasound transducer sensors to a neuromorphic, resistive memories-based computational map. Presented in a paper published recently in Nature Communications, the research team describes development of an auditory-processing system that increases energy efficiency by up [...]
The post CEA-Leti: Neuromorphic Device Uses Up to 5 Orders of Magnitude' Less Energy appeared first on insideHPC.