Yang Ke, Duan Qingxi, Wang Yanghao, Zhang Teng, Yang Yuchao, Huang Ru
Key Laboratory of Microelectronic Devices and Circuits (MOE), Department of Micro/nanoelectronics, Peking University, Beijing 100871, China.
Center for Brain Inspired Chips, Institute for Artificial Intelligence, Peking University, Beijing 100871, China.
Sci Adv. 2020 Aug 14;6(33):eaba9901. doi: 10.1126/sciadv.aba9901. eCollection 2020 Aug.
Optimization problems are ubiquitous in scientific research, engineering, and daily lives. However, solving a complex optimization problem often requires excessive computing resource and time and faces challenges in easily getting trapped into local optima. Here, we propose a memristive optimizer hardware based on a Hopfield network, which introduces transient chaos to simulated annealing in aid of jumping out of the local optima while ensuring convergence. A single memristor crossbar is used to store the weight parameters of a fully connected Hopfield network and adjust the network dynamics in situ. Furthermore, we harness the intrinsic nonlinearity of memristors within the crossbar to implement an efficient and simplified annealing process for the optimization. Solutions of continuous function optimizations on sphere function and Matyas function as well as combinatorial optimization on Max-cut problem are experimentally demonstrated, indicating great potential of the transiently chaotic memristive network in solving optimization problems in general.
优化问题在科学研究、工程和日常生活中无处不在。然而，解决一个复杂的优化问题通常需要大量的计算资源和时间，并且在容易陷入局部最优解方面面临挑战。在此，我们提出一种基于霍普菲尔德网络的忆阻器优化器硬件，它将瞬态混沌引入模拟退火，以帮助跳出局部最优解，同时确保收敛。单个忆阻器交叉阵列用于存储全连接霍普菲尔德网络的权重参数，并就地调整网络动态。此外，我们利用交叉阵列中忆阻器的固有非线性来实现高效且简化的退火过程以进行优化。通过实验证明了在球函数和马蒂亚斯函数上的连续函数优化以及最大割问题的组合优化的解决方案，表明瞬态混沌忆阻器网络在一般优化问题求解中具有巨大潜力。
