Thin Artficial Neurons Made Of 2d Materials Could Advance Ai Computing

A team of researchers from the University of Oxford, IBM Research Europe, and the University of Texas have developed atomically thin artificial neurons by stacking 2D materials. The neurons are able to respond to both optical and electrical signals, enabling the creation of winner-take-all neural networks. These networks have the potential to solve complex problems in machine learning, such as unsupervised learning in clustering and combinatorial optimization. The device is composed of a stack of three 2D materials: graphene, molybdenum disulfide, and tungsten disulfide, and is analog in nature, allowing for gradual changes in stored electronic charge in response to a sequence of electrical or optical signals.