arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.03546cs.LGcond-mat.dis-nncond-mat.mes-hallcond-mat.softcs.ET
收藏

如何训练你的电阻网络:通用平衡传播与解析学习

How to Train Your Resistive Network: Generalized Equilibrium Propagation and Analytical Learning

Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA(明希德电气与计算机工程系,南加州大学,洛杉矶,加利福尼亚州,美国);Center for Nonlinear Studies, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA(非线性研究中心,洛斯阿拉莫斯国家实验室,洛斯阿拉莫斯,新墨西哥州,美国);Theoretical Division (T4), Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA(理论部(T4),洛斯阿拉莫斯国家实验室,洛斯阿拉莫斯,新墨西哥州,美国);CAI-3, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA(CAI-3,洛斯阿拉莫斯国家实验室,洛斯阿拉莫斯,新墨西哥州,美国);University of California, Berkeley, Berkeley, CA, 94720, USA(加州大学伯克利分校,伯克利,加利福尼亚州,美国);Department of Physics, University of Pisa, Largo Bruno Pontecorvo 3, 56127 Pisa, Italy(物理学系,比萨大学,布鲁诺·蓬泰科罗夫大道3号,比萨,意大利)

Jonathan Lin, Aman Desai, Frank Barrows, Francesco Caravelli

AI总结:

本文提出了一种基于图论和解析框架的算法,用于精确计算电阻网络的梯度,实现高效训练,无需复制或读出,且能局部更新电阻值以提升性能。

摘要:

机器学习是一种从数据中提取意义的强大方法;不幸的是,当前的数字硬件极其耗能。存在一种替代的模拟计算实现,其性能可以与传统机器学习相媲美,同时显著更节能。然而,如何在遵守物理(而非数字)性质所施加的局部性约束的情况下训练此类模拟计算系统仍不清楚。局部学习算法如平衡传播和耦合学习已被提出以解决此问题。在本文中,我们开发了一种算法,使用图论和解析框架来精确计算梯度,用于基尔霍夫定律。我们还引入了通用平衡传播,这是一个涵盖广泛海伯学习算法的框架,包括耦合学习和平衡传播,并展示了我们的算法如何进行比较。我们通过数值模拟演示了我们的算法,并证明可以在所有电阻器上训练电阻网络而无需复制或读出,仅在输出层。我们还展示了在解析梯度方法下,可以仅更新一部分电阻值而不影响性能。

英文摘要:

Machine learning is a powerful method of extracting meaning from data; unfortunately, current digital hardware is extremely energy-intensive. There is interest in an alternative analog computing implementation that could match the performance of traditional machine learning while being significantly more energy-efficient. However, it remains unclear how to train such analog computing systems while adhering to locality constraints imposed by the physical (as opposed to digital) nature of these systems. Local learning algorithms such as Equilibrium Propagation and Coupled Learning have been proposed to address this issue. In this paper, we develop an algorithm to exactly calculate gradients using a graph theoretic and analytical framework for Kirchhoff's laws. We also introduce Generalized Equilibrium Propagation, a framework encompassing a broad class of Hebbian learning algorithms, including Coupled Learning and Equilibrium Propagation, and show how our algorithm compares. We demonstrate our algorithm using numerical simulations and show that we can train resistor networks without the need for a replica or readout over all resistors, only at the output layer. We also show that under the analytical gradient approach, it is possible to update only a subset of the resistance values without a strong degradation in performance.

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。

↑