Stochastic single flux quantum neuromorphic computing using magnetically tunable Josephson junctions
This work addresses the need for more flexible and efficient neuromorphic computing hardware, though it appears incremental by building on existing SFQ technology with a new component.
The authors tackled the problem of limited tunability in single flux quantum (SFQ) neuromorphic circuits by introducing magnetic Josephson junctions as a reconfigurable synaptic component, achieving a system capable of over 10^21 neural firings per second with about 1 W dissipation.
Single flux quantum (SFQ) circuits form a natural neuromorphic technology with SFQ pulses and superconducting transmission lines simulating action potentials and axons, respectively. Here we present a new component, magnetic Josephson junctions, that have a tunablility and re-configurability that was lacking from previous SFQ neuromorphic circuits. The nanoscale magnetic structure acts as a tunable synaptic constituent that modifies the junction critical current. These circuits can operate near the thermal limit where stochastic firing of the neurons is an essential component of the technology. This technology has the ability to create complex neural systems with greater than 10^21 neural firings per second with approximately 1 W dissipation.