A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915091894501376 |
|---|---|
| author | Niu, Chang Zhang, Huanyu Xu, Chuanlong Hu, Wenjie Wu, Yunzhuo Wu, Yu Wang, Yadi Wu, Tong Zhu, Yi Zhu, Yinyan Wang, Wenbin Wu, Yizheng Yin, Lifeng Xiao, Jiang Yu, Weichao Guo, Hangwen Shen, Jian |
| author_facet | Niu, Chang Zhang, Huanyu Xu, Chuanlong Hu, Wenjie Wu, Yunzhuo Wu, Yu Wang, Yadi Wu, Tong Zhu, Yi Zhu, Yinyan Wang, Wenbin Wu, Yizheng Yin, Lifeng Xiao, Jiang Yu, Weichao Guo, Hangwen Shen, Jian |
| contents | Physical neural networks using physical materials and devices to mimic synapses and neurons offer an energy-efficient way to implement artificial neural networks. Yet, training physical neural networks are difficult and heavily relies on external computing resources. An emerging concept to solve this issue is called physical self-learning that uses intrinsic physical parameters as trainable weights. Under external inputs (i.e. training data), training is achieved by the natural evolution of physical parameters that intrinsically adapt modern learning rules via autonomous physical process, eliminating the requirements on external computation resources.Here, we demonstrate a real spintronic system that mimics Hopfield neural networks (HNN) and unsupervised learning is intrinsically performed via the evolution of physical process. Using magnetic texture defined conductance matrix as trainable weights, we illustrate that under external voltage inputs, the conductance matrix naturally evolves and adapts Oja's learning algorithm in a gradient descent manner. The self-learning HNN is scalable and can achieve associative memories on patterns with high similarities. The fast spin dynamics and reconfigurability of magnetic textures offer an advantageous platform towards efficient autonomous training directly in materials. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption Niu, Chang Zhang, Huanyu Xu, Chuanlong Hu, Wenjie Wu, Yunzhuo Wu, Yu Wang, Yadi Wu, Tong Zhu, Yi Zhu, Yinyan Wang, Wenbin Wu, Yizheng Yin, Lifeng Xiao, Jiang Yu, Weichao Guo, Hangwen Shen, Jian Disordered Systems and Neural Networks Applied Physics Physical neural networks using physical materials and devices to mimic synapses and neurons offer an energy-efficient way to implement artificial neural networks. Yet, training physical neural networks are difficult and heavily relies on external computing resources. An emerging concept to solve this issue is called physical self-learning that uses intrinsic physical parameters as trainable weights. Under external inputs (i.e. training data), training is achieved by the natural evolution of physical parameters that intrinsically adapt modern learning rules via autonomous physical process, eliminating the requirements on external computation resources.Here, we demonstrate a real spintronic system that mimics Hopfield neural networks (HNN) and unsupervised learning is intrinsically performed via the evolution of physical process. Using magnetic texture defined conductance matrix as trainable weights, we illustrate that under external voltage inputs, the conductance matrix naturally evolves and adapts Oja's learning algorithm in a gradient descent manner. The self-learning HNN is scalable and can achieve associative memories on patterns with high similarities. The fast spin dynamics and reconfigurability of magnetic textures offer an advantageous platform towards efficient autonomous training directly in materials. |
| title | A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption |
| topic | Disordered Systems and Neural Networks Applied Physics |
| url | https://arxiv.org/abs/2501.01853 |