人工神经元

• In order to improve the precision of the model , a new method using self adaption and artificial neural networks to predict rolling force was developed
  为了提高中厚板轧机轧制力的预报精度，采用轧制力模型自适应与人工神经元网络相结合的方法进行中厚板轧制力的在线预报。
• First we introduce its basic idea , typical activating functions , learning rules and its main application : classification & c1ustering , associated memory and optimiza tion
  我们先简要介绍了人工神经元网络的基本思想，典型激活函数，学习规则和主要应用：分类聚类，联想记忆和优化。
• Secondly , this paper has researched the related theories of nerve cell , characters and learning rule of artificial neural networks , the related theories and performance of bp neural networks
  其次，研究了人工神经元的相关理论以及人工神经网络的特征、人工神经网络学习规则和bp神经网络的相关理论和性能。
• Both input and output of the networks are cither procedures or functions . procedure - type ' s inputs to networks relax synchronization instantaneous limit on inputs in the traditional neural network models
  过程式输入放宽了传统神经元网络模型对输入的同步瞬时限制，是传统神经元网络在时间域上的扩展，是更一般化的人工神经元网络模型。
• The deep knowledge repository of temperature profile is yielded based on a large number of numerical solutions of the determinant mathematical model , which increases the " extrapolative ability " and " reliability "
  从基于过程机理模型的数值计算结果出发，结合中试装置的实时操作数据建立了拟定态床层温度的人工神经元网络深层知识库，用于增强神经网络模型的“外推能力”和“可信度” 。
• Firstly , the article clarifies the traditional theory of the stock analyse with its merits and demerits . and then , the article clarifies the basic theory of the neural network which points out the merit of using neural network to analyze the stock market
  论文首先阐述了股票分析的传统理论及其存在的优缺点，接着阐述了人工神经元网络的基本理论，表明了利用人工神经元网络对股票市场进行分析的优点所在。
• Then use the artificial neural network to decouple the high coupling object of the coordinated control system . compared with the traditional pid controller , this intelligent control algorithm can achieve better control effect . zhang de - zhen directed by liu chang - liang
  并用人工神经元网络对存此强耦合的协调控制系统的被控对象实现单向智能解耦控制，和传统的pid控制比较，这种智能控制算法取得了很好的控制效果。
• In this paper , the classical ann approach is improved because of the introduction of inertial coefficient . now the ann can use a bigger rate of learning . with the introduction of former k times sample values , the improved ann method can only used to detect harmonic currents
  本文对传统的ann法进行了改进，通过引入惯性系数的方法，提高了人工神经元自适应的学习率，并采用前k次采样值，使得ann法用于检测畸变电流中谐波电流。
• During the past several decades , in the research of automatic vehicle recognition , classical methods obtained gratifying results ; as well as encountered much difficulty . in this paper , we use artifical neural network to resolve the vehicle recognition problem and attain satisfactory results
  在过去的几十年里对自动汽车识别的研究历程中，经典法取得了一定的可喜成果，但也遇到了许多困难本文将人工神经元网络用于解决汽车识别问题取得了较为满意成果。
• There are lots of non - linear systems in the nature . because classical and morden control methods have common limitation : mathematical model of the plant has to be known in advance . but in fact many plants are intricate uncentaintied and time - varying . in addition , they also are non - linear . though there are methods of system identification in control theories , the identification theories and ways of non - linear and time - varying system are not mature and systematic . it is very difficult to carry out effective real - time control . the neural networks can approximate random non - linear relations and study by itself , and it provides new thoughts and new ways for solving these problems
  由于经典和现代控制方法存在一个共同的局限性：就是要求预先知道被控对象的数学模型，但实际上许多对象具有复杂的不确定性和时变性；此外还具有复杂的非线性。虽然在控制理论中有系统辨识的手段，但是对于非线性时变系统尚无成熟的和系统的辨识理论与方法，要实行有效的实时控制就很难了。人工神经元网络有表示任意非线性关系和自学习等能力，给解决这些问题提供了新思想和新方法。