高阶神经网络的英文

• higher order neural network

• "高阶"英文翻译    high order
• "神经"英文翻译    nerve; nervus
• "网络"英文翻译    network; electric network me ...
• "mp神经网络" 英文翻译 :    mp neural network
• "光神经网络" 英文翻译 :    optical neural network
• "类神经网络" 英文翻译 :    articificial neural network; artificial neural network (ann)
• "神经网络" 英文翻译 :    biological neural network; nerve network; neural network, nn; neural networks; neuron network; neuronic network; neutral networks; nn neural network; radial basis function
• "神经网络的" 英文翻译 :    neural net
• "倒转神经网络" 英文翻译 :    back-propagation neutral network
• "递归神经网络" 英文翻译 :    rnn recurrent neural network
• "电子神经网络" 英文翻译 :    electronic neuron network
• "多层神经网络" 英文翻译 :    multilayer neural network
• "蜂窝神经网络" 英文翻译 :    cnn cellular neural network
• "概率神经网络" 英文翻译 :    pnn probabilistic neural network
• "混合神经网络" 英文翻译 :    hnn hybrid neural network
• "混沌神经网络" 英文翻译 :    chaotic neural network
• "联想神经网络" 英文翻译 :    aann
• "模糊神经网络" 英文翻译 :    fnn fuzzy neural network; fuzzy neural networks; fuzzy-neural network; rfnn
• "人工神经网络" 英文翻译 :    ann artificial neural network; artificial neural nets (ann); artificial neural network
• "神经网络技术" 英文翻译 :    nerual network technique
• "神经网络模拟" 英文翻译 :    simulation of neural network
• "神经网络模型" 英文翻译 :    cmac cerebellar model arithmetic computer; neural network model; snnm
• "神经网络软件" 英文翻译 :    neural-networking software; neural-networks software
• "神经网络算法" 英文翻译 :    neural-net algorithms; nna neural net algorithms
• "神经网络应用" 英文翻译 :    neural network application

• Research on higher - order neural networks
  高阶神经网络模型特性研究
• In this algorithm , author used two technology - the higher - order neural network of single _ layer and hierarchy
  在这一算法中，作者运用了单层的高阶神经网络和分层方法。
• The detailed works are as follows : the finding patterns problems in the time - series data sequence are described , and a new trend logic expression method is introduced , and its algorithm and experiment result of algorithm are given ; time - scries data are disposed , and using the arctg . slope of line as the sample of pattern recognition , so ignoring the aberrance of pattern in the classified . in addition , a new time - series pattern finding algorithm based on higher - order neural network is put forward
  同时给出了本文的具体的工作，主要是：对在时序数据序列中发现模式问题进行了描述，并介绍了一种新的趋势逻辑表示方法，给出了其算法及算法的实验结果；对时序数据进行处理，提出了利用线段的斜率反正切值作为模式识别的样本，从而在分类时忽略模式的畸变；另外，还提出了一个新的基于高阶神经网络的时序模式发现算法。
• The paper studies the existence and global exponential convergence of alomost periodic solutions for high - order neural networks involving variable delay by applying the theory of fixed point and differential inequality technique , some new criteria on the existence and global exponential convergence of almost periodic solutions are obtained
  摘要利用不动点理论和微分不等式分析等技巧，研究了变时滞高阶神经网络概周期解存在性与全局指数收敛性，并且给出了一些新的判别准则。
• Comparing with the other time - series pattern finding algorithm , this one has a few of innovations . firstly , improving time - series pattern finding algorithm from the classified accuracy . secondly , ignoring some aberrance of time - series pattern by the high - order neural network
  同其他的时序模式发现算法相比较，具有几点创新： 1 )从分类精度的角度来改善时序模式发现算法； 2 )通过高阶神经网络，直接利用网络的特性忽略了时序模式的某些畸变； 3 )利用了分层方法，进一步改善分类精度。
• Higher - order neural network of single _ layer has no trouble of hiding layer node , so training speed is fast ; ability of pattern classified increases ; the classification accuracy of pattern is improved without local optimality problem ; hierarchy can make training speed of each node neural network , and improve the classified accuracy of pattern
  单层高阶神经网络没有隐含层节点的困扰，训练速度更快；模式分类能力更为强大；不存在局部最小的问题，模式分类精度更高；模式的不变性构建于网络结构之中等优点。分层方法能加快各节点神经网络的学习速度，也能提高模式划分精度。