arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10895physics.opticscs.ETnlin.CD
收藏

具有纠错反馈的相干Ising机

Coherent Ising machines with error correction feedback

Satoshi Kako, Timothée Leleu, Yoshitaka Inui, Farad Khoyratee, Sam Reifenstein, Yoshihisa Yamamoto

摘要:

一个非平衡的开放耗散神经网络,如一个相干伊辛机的基础上相互耦合的光学参量振荡器,已被提出和证明作为一种新的计算机器硬组合优化问题。然而,在先前提出的方法中存在两个挑战:(1)机器可能被局部最小值所捕获,局部最小值随着问题大小呈指数级增加,以及(2)由于振荡器幅度异质性,机器无法将目标哈密顿量正确映射到神经网络的损失景观上。这两种方法都导致错误的解决方案,而不是正确的答案。在本文中,我们表明,它是可能的,部分地克服这两个问题,但同时通过引入错误检测和纠正反馈机制。所提出的机器实现了有效的采样退化基态和低能量激发态通过其固有的迁移性能在解决方案的搜索过程中。

英文摘要:

A non-equilibrium open-dissipative neural network, such as a coherent Ising machine based on mutually coupled optical parametric oscillators, has been proposed and demonstrated as a novel computing machine for hard combinatorial optimization problems. However, there are two challenges in the previously proposed approach: (1) The machine can be trapped by local minima which increases exponentially with problem size and (2) the machine fails to map a target Hamiltonian correctly on the loss landscape of a neural network due to oscillator amplitude heterogeneity. Both of them lead to erroneous solutions rather than correct answers. In this paper, we show that it is possible to overcome these two problems partially but simultaneously by introducing error detection and correction feedback mechanism. The proposed machine achieves efficient sampling of degenerate ground states and low-energy excited states via its inherent migration property during a solution search process.

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。

↑