Journal
APPLIED PHYSICS LETTERS
Volume 119, Issue 20, Pages -Publisher
AIP Publishing
DOI: 10.1063/5.0072913
Keywords
-
Categories
Funding
- National Key Research Program of China [2020YFA0309100]
- National Natural Science Foundation of China [11991060, 12074075, 12074073]
- Shanghai Municipal Natural Science Foundation [19ZR1402800, 20501130600]
- Shanghai Municipal Science and Technology Major Project [2019SHZDZX01]
- Young Scientist Project of MOE Innovation Platform
Ask authors/readers for more resources
The experimental implementation of width-tunable neurons for training a binary neural network was successful, utilizing the angle-dependent magnetic behavior in an oxide thin film to mimic neurons with width-controllable activation window. This approach achieved a high accuracy of 97.4% when applied to training the MNIST dataset, demonstrating a viable strategy for training neural networks.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available