Fluxonic Processing of Photonic Synapse Events
This work addresses the challenge of converting light signals to electronic domain for dendritic computation in neural systems using superconducting detectors, though it appears incremental as it builds on existing concepts with new circuit implementations.
The paper tackled the problem of processing photonic synapse events in neural systems by introducing circuits based on Josephson junctions and mutual inductors that act as dendrites, enabling temporal filtering, logical operations, and nonlinear transfer functions with efficient use of photons, energy, space, and information.
Much of the information processing performed by a neuron occurs in the dendritic tree. For neural systems using light for communication, it is advantageous to convert signals to the electronic domain at synaptic terminals so dendritic computation can be performed with electrical circuits. Here we present circuits based on Josephson junctions and mutual inductors that act as dendrites, processing signals from synapses receiving single-photon communication events with superconducting detectors. We show simulations of circuits performing basic temporal filtering, logical operations, and nonlinear transfer functions. We further show how the synaptic signal from a single-photon can fan out locally in the electronic domain to enable the dendrites of the receiving neuron to process a photonic synapse event or pulse train in multiple different ways simultaneously. Such a technique makes efficient use of photons, energy, space, and information.