We report an experimental implementation of width-tunable neurons to train a binary neural network. The angle-dependent magnetic behavior in an oxide thin film highly mimics neurons with width-controllable activation window, providing an opportunity to train the activation functions and weights toward binary values. We apply this feature to train the MNIST dataset using a 684-800-10 fully connected network and achieve a high accuracy of 97.4%, thus opening an implementation strategy toward training neural networks.
Implementation of artificial neurons with tunable width via magnetic anisotropy
Chang Niu, Yuansheng Zhao, Wenjie Hu, Qian Shi, Tian Miao, Yang Yu, Lifeng Yin, Jiang Xiao, Hangwen Guo, Jian Shen; Implementation of artificial neurons with tunable width via magnetic anisotropy. Appl. Phys. Lett. 15 November 2021; 119 (20): 204101. https://doi.org/10.1063/5.0072913
Download citation file: