Neuromorphic computing is an emerging computing paradigm inspired by the structure and functionality of biological neural systems. This review examines the fundamental principles of neuromorphic computing, with a particular focus on artificial synaptic devices and their role in enabling energy-efficient, brain-inspired computation. The paper discusses major synaptic technologies, including memristors, phase-change memory, ferroelectric devices, spintronic devices, and electrochemical synapses, and evaluates their advantages, limitations, and performance trade-offs. It further explores array architectures, learning algorithms, system integration challenges, and real-world applications in edge AI and intelligent sensing. Based on recent literature, the study identifies key research gaps and proposes future directions for the development of scalable and efficient neuromorphic systems. A conceptual agricultural IoT edge-monitoring use case is also presented to illustrate the potential impact of neuromorphic hardware in practical deployments.
Hira Fatima (Wed,) studied this question.