The extensive development of the field of spiking neural networks has led to many areas of research that have a direct impact on people’s lives. As the most bio-similar of all neural networks, spiking neural networks not only allow for the solution of recognition and clustering problems (including dynamics), but they also contribute to the growing understanding of the human nervous system. Our analysis has shown that hardware implementation is of great importance, since the specifics of the physical processes in the network cells affect their ability to simulate the neural activity of living neural tissue, the efficiency of certain stages of information processing, storage and transmission. This survey reviews existing hardware neuromorphic implementations of bio-inspired spiking networks in the ”semiconductor”, ”superconductor”, and ”optical” domains. Special attention is given to the potentials for effective ”hybrids” of different approaches.

We demonstrate the programmable control of kinetic soliton dynamics in all-Josephson-junction (all-JJ) networks through a novel tunable cell design. This cell enables on-demand switching of transmission lines and operates across defined parameter regimes supporting diverse dynamical modes. By introducing a structural asymmetry into a transmission line, we implement a Josephson diode that enforces unidirectional soliton propagation. The programmability of the kinetic inductance then provides a crucial mechanism to selectively enable or disable this diode functionality. By engineering artificial inhomogeneity into the circuit architecture, we enhance robustness in all-JJ logic circuits, 2D transmission line all-JJ lattices, and neuromorphic computing systems.

We demonstrate programmable control of kinetic soliton dynamics in all-Josephson-junction (all-JJ) networks through a novel tunable cell design. This cell enables on-demand switching of transmission lines and operates across defined parameter regimes supporting diverse dynamical modes. By introducing a structural asymmetry into a transmission line, we implement a Josephson diode that enforces unidirectional soliton propagation. The programmability of the kinetic inductance then provides a crucial mechanism to selectively enable or disable this diode functionality. By engineering artificial inhomogeneity into the circuit architecture, we enhance robustness in all-JJ logic circuits, 2D transmission line all-JJ lattices, and neuromorphic computing systems.

In all-Josephson-junction (all-JJ) logic, cell area is determined by the size of Josephson junctions, enabling intrinsically compact layouts. Tunable kinetic inductance offers a route to add circuit reconfigurability, pushing further scaling within the same all-JJ framework. In this work we present a set of basic cells for reconfigurable superconducting “kinemonics” that exploit tunable kinetic inductances of a multilayer nanostructure to realise multiple logic functions within a single compact circuit. We then combine these gates into a universal programmable logic cell consisting of only four reconfigurable gates supplemented by a single tunable kinetic-inductance key and demonstrate that it can realise all sixteen two-input Boolean functions, making it an analogue of a look-up table with in-hardware reconfigurability. We also discuss how the same principle can be used in superconducting neuromorphic circuits, where tunable kinetic inductance controls routing, coincidence detection, inhibition, and delay for soliton-like spikes in neuron-like elements.

In all-Josephson-junction (all-JJ) logic, cell area is determined by the size of Josephson junctions, enabling intrinsically compact layouts. Tunable kinetic inductance offers a route to add circuit reconfigurability, pushing further scaling within the same all-JJ framework. In this work we present a set of basic cells for reconfigurable superconducting “kinemonics” that exploit tunable kinetic inductances of a multi-layer nanostructure to realise multiple logic functions within a single compact circuit. We then combine these gates into a universal programmable logic cell consisting of only four reconfigurable gates supplemented by a single tunable kinetic-inductance key and demonstrate that it can realise all sixteen two-input Boolean functions, making it an analogue of a look-up table with in-hardware reconfigurability. We also discuss how the same principle can be used in superconducting neuromorphic circuits, where tunable kinetic inductance controls routing, coincidence detection, inhibition, and delay for soliton-like spikes in neuron-like elements.