Using Stochastic Spiking Neural Networks on SpiNNaker to Solve Constraint Satisfaction Problems.
Using Stochastic Spiking Neural Networks on SpiNNaker to Solve Constraint Satisfaction Problems.
复制标题
DOI：
10.3389/fnins.2017.00714
复制
发表时间：
2017
影响因子：
4.3
通讯作者：
Furber SB
中科院分区：
文献类型：
--
作者：
Fonseca Guerra GA;Furber SB
约束满足问题（CSP）是许多科学和技术应用的核心。然而，CSP属于NP-完全复杂性类，其有效算法的存在（或不存在）仍然是计算复杂性理论中未解决的主要问题。面对这一根本性的困难，我们使用解析和近似方法来处理NP的实例（例如，决策和硬优化问题）。人类大脑使用尖峰神经网络（SNN）在感知和行为方面有效地处理CSP，最近的研究表明，SNN中嵌入的噪声可以用作计算资源来解决CSP。在这里，我们提供了一个软件框架，用于在SpiNNaker大规模并行神经形态硬件上实现这种嘈杂的神经求解器，进一步展示了它们实现随机搜索的潜力，该搜索解决了表示为CSP的P和NP问题的实例。这有助于探索新的优化策略和理解SNN的计算能力。我们通过解决数独难题和地图颜色问题的困难实例来展示框架的基本原理，并探索其在旋转眼镜中的应用。求解器作为一个随机动力系统工作，它被求解CSP的配置所吸引。噪声允许对配置空间进行最佳探索，寻找所有约束的可满足性;如果不连续地应用，它也可以迫使系统跳到一个新的随机配置，有效地导致重新启动。
Constraint satisfaction problems (CSP) are at the core of numerous scientific and technological applications. However, CSPs belong to the NP-complete complexity class, for which the existence (or not) of efficient algorithms remains a major unsolved question in computational complexity theory. In the face of this fundamental difficulty heuristics and approximation methods are used to approach instances of NP (e.g., decision and hard optimization problems). The human brain efficiently handles CSPs both in perception and behavior using spiking neural networks (SNNs), and recent studies have demonstrated that the noise embedded within an SNN can be used as a computational resource to solve CSPs. Here, we provide a software framework for the implementation of such noisy neural solvers on the SpiNNaker massively parallel neuromorphic hardware, further demonstrating their potential to implement a stochastic search that solves instances of P and NP problems expressed as CSPs. This facilitates the exploration of new optimization strategies and the understanding of the computational abilities of SNNs. We demonstrate the basic principles of the framework by solving difficult instances of the Sudoku puzzle and of the map color problem, and explore its application to spin glasses. The solver works as a stochastic dynamical system, which is attracted by the configuration that solves the CSP. The noise allows an optimal exploration of the space of configurations, looking for the satisfiability of all the constraints; if applied discontinuously, it can also force the system to leap to a new random configuration effectively causing a restart.
登录
查看更多内容
影响因子：
4.6
作者：
Ercsey-Ravasz, Maria;Toroczkai, Zoltan
通讯作者：
Toroczkai, Zoltan
影响因子：
20.6
作者：
Furber, Steve B.;Galluppi, Francesco;Plana, Luis A.
通讯作者：
Plana, Luis A.
影响因子：
3.7
作者：
Clarke, Aaron Michael;Friedrich, Johannes;Herzog, Michael H.
通讯作者：
Herzog, Michael H.
影响因子：
3.7
作者：
Furber, Steve B.;Lester, David R.;Brown, Andrew D.
通讯作者：
Brown, Andrew D.
DOI：
10.1088/0305-4470/15/10/028
发表时间：
1982-01-01
期刊：
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL
影响因子：
--
作者：
BARAHONA, F
通讯作者：
BARAHONA, F