1. Implementation of artificial neurons with tunable width via magnetic anisotropy
- Author
-
Jian Shen, Yang Yu, Jiang Xiao, Qian Shi, Hangwen Guo, Wenjie Hu, Lifeng Yin, Chang Niu, Yuansheng Zhao, and Tian Miao
- Subjects
Magnetic anisotropy ,Physics and Astronomy (miscellaneous) ,Artificial neural network ,Computer science ,Feature (machine learning) ,Binary number ,Topology ,Binary neural network ,MNIST database - Abstract
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.
- Published
- 2021
- Full Text
- View/download PDF