Communications of the ACM
Brain-Derived Computing Beyond Von Neumann
Heidelberg University professor Karlheinz Meier says that neuromorphic computers "are systems with the same massive parallelism as the brain."
Credit: Jeff Cameron Collingwood/Shutterstock
In an interview, Heidelberg University professor Karlheinz Meier discusses the emerging field of neuromorphic computing and Europe's ambitious Human Brain Project (HBP).
"Neuromorphic computers are systems with the same massive parallelism as the brain and the same functions on the microscopic and the macroscopic level," Meier says. "Communication between cells is carried out by stereotypic action potentials that propagate through the network asynchronously and in continuous time."
Meier says neuromorphic systems' most valuable quality is their ability to self-configure based on their input data. He also says the success of HBP hinges on collaboration between neurobiologists, theoretical neuroscientists, mathematicians, physicists, and engineers.
Meier says HBP will follow two complementary strategies for assembling neuromorphic computers, and the project's goal is the construction and operation of six technology platforms that aggregate neuroscience data and apply it to brain models on an exascale system, from which researchers will attempt to derive very-large-scale neuromorphic computers.
"By the end of the 30-month ramp-up phase, HBP plans to operate a physical model system with 4 million neurons and 1 billion synapses in Heidelberg, and a system of 0.5 million ARM cores in Manchester, UK," Meier notes.
From Scientific Computing
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found