Spiking Neural P Systems with Weighted Synapses
Spiking Neural P Systems with Weighted Synapses
复制标题
具有加权突触的尖峰神经 P 系统
DOI：
10.1007/s11063-011-9201-1
复制
发表时间：
2012-02-01
影响因子：
3.1
通讯作者：
Jiang, Yun
中科院分区：
文献类型：
--
作者：
Pan, Linqiang;Zeng, Xiangxiang;Jiang, Yun
尖峰神经P系统是一类分布式并行计算模型，其灵感来自于神经元通过电脉冲相互通信的方式，其中每对连接的神经元之间存在突触。然而，在生物系统中，每对连接的神经元可以有几个突触。在这项研究中，受到这种生物学观察的启发，在尖峰神经P系统中的突触被赋予整数权重，表示每对连接的神经元的突触数量。以突触的权值为代价，可以构造出相当小的通用脉冲神经P系统。具体来说，一个通用的尖峰神经P系统与标准的规则和权重有38个神经元的计算功能的设备，作为发电机的数字集，我们发现一个通用的系统与标准的规则和权重有36个神经元。
Spiking neural P systems are a class of distributed parallel computing models inspired from the way neurons communicate with each other by means of electrical impulses, where there is a synapse between each pair of connected neurons. However, in a biological system, there can be several synapses for each pair of connected neurons. In this study, inspired by this biological observation, synapses in a spiking neural P system are endowed with integer weight denoting the number of synapses for each pair of connected neurons. With the price of weight on synapses, quite small universal spiking neural P systems can be constructed. Specifically, a universal spiking neural P system with standard rules and weight having 38 neurons is produced as device of computing functions; as generator of sets of numbers, we find a universal system with standard rules and weight having 36 neurons.