AI chips could get a sense of time with memristor that can be tuned

Tunable composition and structural disorder in single-crystalline ESO thin films on epitaxial YBCO electrodes. Credit: Nature Electronics (2024). DOI: 10.1038/s41928-024-01169-1 Artificial neural networks may soon be able to process time-dependent information, such as audio and video data, more efficiently. The first memristor with a “relaxation time” that can be tuned is reported today in Nature Electronics, in a study led by the University of Michigan. Memristors, electrical components that store information in their electrical resistance, could reduce AI’s energy needs by about a factor of 90 compared to today’s graphical Read More