Answers are grounded in this paper and cite their sources.
The development of artificial intelligence has continuously amplified the demand for neuromorphic computing and memory. However, the separation of computing and memory units in the traditional von Neumann architecture and the slowdown of Moore’s Law led to high power consumption and time delay in the handling of a large amount of data, which cannot meet the urgent needs of efficient and high-speed computing in the current rapid development of information technology. It is urgent to develop a novel computing paradigm to meet the challenge. Brain-inspired neuromorphic devices based on memory and computing-integrated architecture have the advantages of high parallelism and ultralow power consumption and are expected to overcome the von Neumann bottleneck. This article reviews the latest advances in flexible neuromorphic devices implemented by emerging transition metal dichalcogenide (TMDC) materials, from device design to system integration. First, the material structures/properties and synthetic methods of TMDCs are introduced. Then, the applications of TMDCs in flexible neuromorphic devices (artificial synapses and neurons) are discussed in detail. Furthermore, the potential applications of flexible neuromorphic devices for sensory recognition, including visual, tactile, auditory, and multisensory, are elaborated. Finally, the challenges in materials preparation, processing compatibility, device size miniaturization, energy consumption, and the prospect of future applications of flexible neuromorphic devices based on TMDCs are summarized.
No takes yet. Share an insight, caveat, or question.
Ma et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: