AMHERST, Mass. – Engineers at the University of Massachusetts Amherst are leading a team of international researchers that has just published results on neuromorphic computing, where microprocessors are configured more like human brains than conventional computer chips with the goal of both building better computers and advancing our understanding of the human brain. The paper appears in the February online issue of Nature Electronics and is a follow-up to a 2017 paper in Nature Materials by the same team.
Professors Joshua Yang and Qiangfei Xia of the UMass Amherst electrical and computer engineering (ECE) department led the 24-person international team of researchers from Loughborough University in the U.K., Hewlett Packard Labs, the U.S. Air Force Research Lab, and the Institute of Microelectronics, Tsinghua University, in China.
Yang and Xia say neuromorphic computing is one of the most promising transformative computing technologies currently under intensive study. Memristive devices are a key element of their new research. Memristors are electrical resistance switches that can alter their resistance based on the history of applied voltage and current. These devices can store and process information at the same location on a chip and offer several key performance characteristics that exceed conventional integrated circuit technology.
The researchers say in this latest paper that for the first time they can use these neurons with nonvolatile memristive synapses to build fully memristive artificial neural networks. “With these integrated networks, we experimentally demonstrate unsupervised synaptic weight updating and pattern classification.”
Nature Electronics says it is “interested in the best research from all areas of electronics, incorporating the work of scientists, engineers, and researchers in industry.” The journal recently published another research work led by the UMass Amherst team as the cover article for its inaugural issue in January of 2018.
In addition to Yang and Xia, the UMass Amherst authors are Zhongrui Wang, Saumil Joshi, Wenhao Song, Rivu Midya, Yunning Li, Mingyi Rao, Peng Yan, Shiva Asapu, Ye Zhuo, Hao Jiang, Peng Lin, Can Li, Jung Ho Yoon and Navnidhi K. Upadhyay; Sergey Savel’ev of Loughborough University; Jiaming Zhang, Miao Hu, John Paul Strachan and R. Stanley Williams from Hewlett Packard Labs; Mark Barnell and Qing Wu from the U.S. Air Force Research Lab, and Huaqiang Wu from the Tsinghua University.