High-throughput machine learning-guided exploration of chalcogenide materials for resistive switching devices

Abstract

Chalcogenide glasses have emerged as promising candidates for neuromorphic computing and resistive switching memory devices due to their unique electronic properties and structural flexibility. However, traditional materials discovery approaches are time-consuming and resource-intensive, limiting exploration of the vast compositional space available in these systems. Machine learning (ML) combined with high-throughput (HT) experimental techniques offers a paradigm shift in accelerating the discovery of novel functional materials with targeted properties.