Low-Power Memristor for Neuromorphic Computing: From Materials to Applications

• This review describes various types of low-power memristors, demonstrating their potential for a wide range of applications. • This review summarizes low-power memristors for multi-level storage, digital logic, and neuromorphic computing, emphasizing their use as artificial synapses and neurons in artificial neural network, convolutional neural network, and spiking neural network, along with 1T1R and 1S1R crossbar array designs. • Further exploration is essential to overcome limitations and unlock the full potential of low-power memristors for in-memory computing and AI. • The paper discusses the selection of functional materials for low-power memristors, including ion transport, phase change, magnetoresistive, and ferroelectric materials.