With the growing energy demands of modern computers based on von Neumann architecture, the need for more energy-efficient computing solutions has become increasingly urgent. This has led to a shift towards non-von Neumann computing paradigms, particularly those inspired by the brain’s neural network architecture. Artificial Neural Networks (ANNs), which emulate the structure and function of biological neurons and synapses, have gained significant attention in this context. These networks, when built on superconducting elements, promise a dramatic reduction in energy consumption, addressing the key limitations of current semiconductor-based computing systems. In this work, we investigate superconducting artificial neurons based on superconducting spin valves and artificial synapses composed of hybrid nanostructures. The study focuses on superconductor/ferromagnet layered hybrid nanostructures, highlighting their potential in superconducting spintronics and energy-efficient computing. Study of proximity effect in the multilayer superconductor/ferromagnetic (S/F) nanostructures with ferromagnetic Co layers of various thicknesses and coercive fields, as well as superconducting Nb layers of constant thickness equal to the coherence length of superconductor were done and analysed. The results of the design and research of artificial neurons based on superconducting spin valves and superconducting synapses based on superconductor-ferromagnetic Nb/Co hybrid nanostructures are presented.