Kurzweil AI January 22, 2018
A team of researchers in the US (MIT, Arizona State University) has demonstrated analog resistive switching devices that possess desired characteristics for neuromorphic computing networks with minimal performance variations. They used a single-crystalline SiGe layer epitaxially grown on Si as a switching medium. It utilizes threading dislocations in SiGe to confine metal filaments in a defined, one-dimensional channel which results in drastically enhanced switching uniformity and long retention/high endurance with a high analog on/off ratio. In tests their neural network hardware recognized handwritten samples 95 percent of the time, compared to the 97 percent accuracy of existing software algorithm… read more. TECHNICAL ARTICLE
Biological synapse structure (Credit: Thomas Splettstoesser/CC)