基于MapReduce模型的Hopfield神经网络联想记忆算法  

HOPFIELD NEURAL NETWORK ASSOCIATIVE MEMORY ALGORITHM BASED ON MAPREDUCE MODEL

作　　者：曾俊[1] 

机构地区：[1]长江师范学院数学与计算机学院

出　　处：《计算机应用与软件》2013年第8期267-270,共4页Computer Applications and Software

摘　　要：Hopfield神经网络以良好的联想记忆功能、容错性而得到广泛的应用。然而,云计算平台下,面对海量数据时它并不能在单机上存储高维度模式以及获得良好的性能。另外,传统的联想记忆网络数据分布存储,使得MapReduce结构可以很好地解决并行化和分布性的问题。根据以上原理,提出一种MRHAM(MapReduce-based Hopfield Network for Association Memory)算法,对传统的Hopfield联想记忆算法采用MapReduce架构实现大规模并行化处理。通过实验验证在大规模数据量下获得比传统Hopfield联想记忆算法更好的性能,对于海量数据的基于内容存储、联想记忆有重要意义。Hopfield network is a widely used neural network for its excellent performance in associative memory and fault tolerafit property. However, on cloud computing platform, it is not able to store high-dimensional mode in a single computer and to acquire good performance when come across massive data. Besides, the data storage in traditional associative memory networks is distributed, this enables the MapReduce structure can well solve the parallelisation and distribution problems. According to the principle above, we put forward an algorithm of MRHAM （ MapReduce-based Hopfield Network for Associative Memory） which uses MapReduce architecture to implement large- scale parallelised processing on traditional Hopfield associative memory algorithm. It is verified through experiment that the performance of MRHAM algorithm acquired in massive amount of data is better than that of the traditional Hopfield associative memory algorithm; this has important significance to massive data for content-based storage and associative memory.

关 键 词：MAPREDUCE HOPFIELD 联想记忆 云平台 大规模数据 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]