An active dendritic tree can mitigate fan-in limitations in superconducting neurons
This addresses a hardware bottleneck for neuromorphic computing with superconducting circuits, offering a specific improvement for more efficient neuron designs.
The paper tackled the problem of fan-in limitations in superconducting neurons by showing that an active dendritic tree significantly reduces the fraction of synapses needed to drive a neuron to threshold, enhancing computational abilities and enabling spiking with sparse input activity.
Superconducting electronic circuits have much to offer with regard to neuromorphic hardware. Superconducting quantum interference devices (SQUIDs) can serve as an active element to perform the thresholding operation of a neuron's soma. However, a SQUID has a response function that is periodic in the applied signal. We show theoretically that if one restricts the total input to a SQUID to maintain a monotonically increasing response, a large fraction of synapses must be active to drive a neuron to threshold. We then demonstrate that an active dendritic tree (also based on SQUIDs) can significantly reduce the fraction of synapses that must be active to drive the neuron to threshold. In this context, the inclusion of a dendritic tree provides the dual benefits of enhancing the computational abilities of each neuron and allowing the neuron to spike with sparse input activity.