R&D: Implementation of Binary Neural Network on Passive Array of Magnetic Tunnel Junctions

IEEE Xplore has published, in 2022 IEEE 33rd Magnetic Recording Conference (TMRC) proceedings, an article written by Jonathan M. Goodwill, Physical Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA, Nitin Prasad, Associate, Physical Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA , and Department of Chemistry and Biochemistry, University of Maryland, College Park, MD, USA, Brian D. Hoskins,Matthew W. Daniels, Physical Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA, Advait Madhavan, Associate, Physical Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA, and Institute for Research in Electronics and Applied Physics, University of Maryland, College Park, MD, USA, Lei Wan, Tiffany S. Santos, Michael Tran, Jordan A. Katine, Patrick M. Braganca, Western Digital Research Center, Western Digital Corporation, San Jose, California, USA, Mark D. Stiles, and Jabez J. McClelland, Physical Measurement Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA.

Abstract: “Magnetic tunnel junctions (MTJs) provide an attractive platform for implementing neural networks because of their simplicity, non-volatility, and scalability. However, in hardware realizations, device variations, write errors, and parasitic resistance degrade performance. To quantify such effects, we perform inference experiments on a 2-layer perceptron constructed from a 15 x 15 passive array of MTJs, examining classification accuracy and write fidelity. Despite imperfections, we achieve median accuracy of 95.3% with proper tuning of network parameters. The success of this tuning process shows that new metrics are needed to characterize and optimize networks reproduced in mixed signal hardware.“