arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.01853cond-mat.dis-nnphysics.app-ph
收藏

一种具有内禀梯度下降自适应的自学习磁性Hopfield神经网络

A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption

Chang Niu, Huanyu Zhang, Chuanlong Xu, Wenjie Hu, Yunzhuo Wu, Yu Wu, Yadi Wang, Tong Wu, Yi Zhu, Yinyan Zhu, Wenbin Wang, Yizheng Wu, Lifeng Yin, Jiang Xiao, We… 展开作者

Chang Niu, Huanyu Zhang, Chuanlong Xu, Wenjie Hu, Yunzhuo Wu, Yu Wu, Yadi Wang, Tong Wu, Yi Zhu, Yinyan Zhu, Wenbin Wang, Yizheng Wu, Lifeng Yin, Jiang Xiao, Weichao Yu, Hangwen Guo, Jian Shen

AI总结:

本文提出一种基于磁织构导电矩阵的自学习Hopfield神经网络,利用内禀物理过程以梯度下降方式实现Oja学习算法,无需外部计算资源即可完成高相似度模式的联想记忆。

摘要:

利用物理材料和器件模拟突触与神经元的物理神经网络,为实现人工神经网络提供了一种高能效的途径。然而,物理神经网络的训练十分困难,并且严重依赖外部计算资源。解决这一问题的一个新兴概念被称为物理自学习,它利用内禀物理参数作为可训练权重。在外部输入(即训练数据)作用下,训练通过物理参数的自然演化实现,这些参数借助自主物理过程内禀地适配现代学习规则,从而消除了对外部计算资源的需求。在此,我们展示了一个真实的磁自旋电子学系统,该系统模拟Hopfield神经网络(HNN),并通过物理过程的演化内禀地执行无监督学习。利用磁织构定义的导电矩阵作为可训练权重,我们证明在外部电压输入下,导电矩阵会自然演化,并以梯度下降方式适配Oja学习算法。该自学习HNN具有可扩展性,并且能够在相似度较高的模式上实现联想记忆。磁织构的快速自旋动力学和可重构性为直接在材料中实现高效自主训练提供了一个有利平台。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑