Deep Learning Meets Neuromorphic Hardware

This Special Issue focuses on unconventional computing paradigms for artificial intelligence and machine learning that extend beyond traditional digital architectures, encompassing novel computational frameworks, algorithms, and hardware substrates. We invite contributions on neuromorphic, photonic, quantum, analog, in-memory, reservoir, and in-material computing, as well as other emerging physical and bio-inspired approaches, with particular emphasis on their application to artificial intelligence, machine learning, and data-driven computation. Topics include hardware architectures, computational models, algorithms, learning mechanisms, and hardware–software co-design strategies that exploit the dynamics and constraints of unconventional substrates. The issue aims to foster interdisciplinary research at the intersection of artificial intelligence, computer science, engineering, physics, materials science, dynamical systems, unconventional computing, and emerging hardware technologies, highlighting innovative approaches to efficient, adaptive, scalable, and sustainable computation.