Recent Advances of Graphene and Related Materials in Artificial Intelligence

Biological brains perform real-time processing of unstructured data with ultralow energy consumption and represent the most efficient computing systems. Emulating working principles biological brings a revolutionary breakthrough in artificial intelligence (AI), generating two kinds imitation approaches including machine learning (ML) neuromorphic (NC) neurons/synapses. Herein this review, general description ML methods, concept, principle synapses (ASs) NC derived from synapses, their relationships, is provided. Graphene, one representative 2D materials, arouses considerable attention due to its unique structure properties. The application properties prediction (electronic properties, mechanical thermal cytotoxicity), recognition (atomic structure, microscopic dimensions/shapes), inverse design (composition, structure), task (chemical recognition, motion 3D imaging) graphene derivatives composites are summarized, corresponding methods discussed case studies. Recent progress development graphene-based ASs (synaptic transistors memristors) briefly introduced, where materials serve as channel synaptic transistors, memristive or back electrodes memristors. Finally, main challenges prospects graphene-incorporated presented.