Title: NIST Develops Energy-Efficient Artificial Synapse Using Superconducting Josephson Junctions
Summary:
The National Institute of Standards and Technology (NIST) has created a new type of artificial synapse based on superconducting Josephson junctions with magnetic clusters in the barrier. This innovative technology allows for dynamic reconfiguration of the synapse’s properties, making it more energy-efficient than current neuromorphic hardware.
Key points:
– The artificial synapse uses superconducting Josephson junctions with magnetic clusters in the barrier
– The critical current of each junction can be tuned using input voltage spikes, changing the spin order of the magnetic clusters
– The technology operates in the stochastic regime, with spiking energy comparable to thermal energy
– It is more energy-efficient than existing neuromorphic hardware, even when accounting for cooling requirements
– The breakthrough could enable more complex computing systems due to improved energy efficiency
The research team, led by Michael Schneider, Stephen Russek, William Rippard, and Matthew Pufall, has demonstrated the potential for this technology to revolutionize energy-efficient computing. By operating at 4 K temperatures, the devices offer a promising path forward for developing advanced neuromorphic systems.
Source: https://www.nist.gov/tpo/patent-month-october-2020
Keywords: Superconducting, Josephson, Neuromorphic
