从网络结构上看，它是一种混合型的神经网络，由下面三层的前馈网络和上层的反馈网络组成。
The network structure of PBCA is a mixed structure composed of feed-forward network and feedback network.
设计了一种实用的面向普通工程技术人员，图形化用户界面，支持多种神经网络网型的神经网络开发软件。
A practical developing software of neural network supporting many kinds of neural networks is designed. The software is general technical engineering people oriented and with graphic user interface.
有意思的是，神经网络是一种对学习型评估的进化，算法经过训练后其行为就像是一个人类专家。
It is interesting to note that Neural Networks is an evolution of learning-oriented estimation, in which the method algorithm is trained to behave like a human expert.
延续了本课题组在挤出吹塑中利用人工神经网络(ANN)预测型坯尺寸的工作，建立一个新的ANN模型。
It is the continuity work on predicting parison dimensions in extrusion blow molding by means of the artificial neural network (ANN) method, and established a new ANN model.
以人工神经网络的前馈型网络为基础结构，基于反向传播算法进行学习和训练来拟和证券价格指数的运动趋势。
In this model, back propagation algorithm based on forward networks was conducted to learn information of historical data and to train the network weights.
然后，基于某型小卫星的姿态控制问题，设计了高精度定向阶段的神经网络补偿控制器。
Then, base on the problem of attitude control of a satellite under development, we design a NN compensation controller for high accuracy orientation phase.
我们发现语义神经网络以语义分析为主，这正好符合汉语作为分析型语言的特点。
We find that the Semantic Neural Network relies on semantic analysis mainly, which just accords with the characteristics of Chinese as the language of analytical type.
本文介绍了一种基于模糊神经网络的智能型火灾报警系统。
This Paper discusses an intelligent fire alarm system based on fuzzy neural network.
针对传统专家系统和神经网络的各自特点，将两者有机结合，构造了一种基于神经网络的混合型故障诊断专家系统。
According to the characters of traditional expert system and neural network, a neutral - network - based mixed fault diagnosis expert system was designed.
在瞄准控制模块中，用前馈型神经网络实现从信息空间到任务控制空间的映照。
A forward neural network is used to perform the maps from information space to task control space in gazing control module.
提出一种用最小二乘支持向量机(LS - SVM)构造函数链接型神经网络(FLANN)逆系统的传感器动态补偿新方法。
A dynamic compensating method for transducers is presented based on functional link artificial neural networks (FLANN) inverse system constructed by least squares-support vector machine (LS-SVM).
提出了一种带模糊补偿的神经网络辨识器，并应用在某型涡扇发动机转速控制系统中。
A new neural network algorithm with fuzzy logic compensation was proposed and applied to an aero-engine rotating speed control system.
提出并实现了一种结合前馈型神经网络和K最近邻的文本分类算法。
This paper put forward and carried out a text classification method using feed-forward neural network and K-nearest neighbor.
其次，论文设计了两种用于入口匝道控制的神经网络控制器——直接型和积分型。
Secondly, two neural networks controllers for the ramp control are developed, which are the direct controller and the PI controller.
小波神经网络可以看作是以小波函数为基底的一种函数连接型网络，也可以认为是径向基函数(RBF)网络的推广。
Wavelet neural networks can be regard as not only the function-linked networks based wavelet function, but also the extension of Radical basis function (RBF) networks.
改进型BP神经网络分类识别系统在遥感图像的自动分类识别上有广阔的应用前景。
The modified BP Nerve Network Classify and Identify System has a very wide application foreground in TM images.
该网络把级数中的函数看成非线性神经元，建立油藏系统的函数型连接人工神经网络模型。
In the net, the functions are served as nonlinear neural units to establish function link artificial neural networks models of oil reservoir systems.
采用人工神经网络方法预测了受模口温度和挤出流率影响的型坯成型阶段的膨胀。
Neural network method was used to investigate the parison swell affected by the die temperature and extrusion flow rate.
提出了利用模态频率、模态振型和模态柔度组合指标作为神经网络修正的输入参数。
And we suggest that mode frequencies, mode shapes and mode flexibility are regarded as input parameters of neural network modification.
这种用改进了的自组织方法所构成的GMDH型神经网络可以应用于混沌时间序列预测。
An improved GMDH-type neural network and its application to predicting chaotic time series are proposed.
把填充函数法与BP算法相结合，提出一种训练前向神经网络的混合型全局优化新算法。
This paper proposes a new global optimization technique in which combines the filled function method and BP algorithm for Training feedforward neural networks.
介绍了基于新型非加热型半导体气体传感器和人工神经网络的气体定量检测系统。
An experiment system for the gas quantitative detection, which is based on non-heating semiconductor gas sensor and artificial network, is introduced in this paper.
利用竞争型神经网络，实现对凝汽器系统的故障诊断。
Using competitive neural network to diagnose the fault in condenser system.
给出了电流继电器、圆特性以及四边型特性阻抗继电器的神经网络模型，并证明了三种模型都具有很强的自适应性。
The paper presents the neural network models of the current relay, impedance relay of circle character and polygon character, and proves that these models have better adaptability.
椭球单元通过高斯分布逼近形成各模式类的决策区域，是一种非常适合于模式识别任务的前馈型人工神经网络模型。
Neural Networks with Ellipsoidal Activation Functions closes in upon a decision making region by Gauss distribution for various patterns and is adapted to fault diagnosis well.
在泵系统故障诊断与监测中的应用表明，混合型神经网络能可靠地进行水泵机组故障模式的识别。
Its application to fault diagnosis and state monitoring for a pump system shows that the hybrid neural network may recognize the fault modes in pump units reliably.
本文运用模糊神经网络原理，采用学习结合型FNN方法，针对两种不同材料梁的大变形进行了网络建模和预测的数值仿真。
Principles of fuzzy neural network and FNN method are adopted for the numerical simulation of network modeling and forecasting of beams with finite deformation of two different materials.
讨论了线性二次型最优控制理论在神经网络PID控制系统中的应用。
This paper discusses the application of linear quadratic optimal control theory in network PID control system.
基于前向型神经网络理论的时间序列分析跳出了传统的建立主观模型的局限，通过时间序列的内在规律作出分析与预测。
Time series analysis based on neural networks theory cross through traditional frame of subjective model draw out prediction on the inner rules of linear time series data.
基于前向型神经网络理论的时间序列分析跳出了传统的建立主观模型的局限，通过时间序列的内在规律作出分析与预测。
Time series analysis based on neural networks theory cross through traditional frame of subjective model draw out prediction on the inner rules of linear time series data.
应用推荐