Combining fractal calculating dimension with multi layer neural network, a diagnosis method named as fractal neural network is built.
将分形计算维数概念与多层感知器神经网络结合，建立了机械设备的分形神经网络诊断方法。
The application of multi-layer feed-forward artificial neural network in fault equipment diagnosis includes feature value setting of equipment operation condition and fault judgment.
多层前馈人工神经网络在装备故障诊断中的应用含设备运行状态特征值设定和故障判定。
This paper describes the use of multi-layer perception model of neural network in speech recognition.
本文研究神经网络的多层感知器模型在语音识别中的应用。
We have studied that the variable structure neural network for single hidden layer and multi hidden layer.
先后研究了神经网络单隐层和多隐层的变化情况。
After the rules were obtained based on rough set theory, the rules were embedded in the neural network, so that a kind of strong coupling multi-layer neural network was constructed.
利用粗糙集理论进行规则提取后，将规则结果融入神经网络中，从而构造了一种强耦合多层模糊粗糙神经网络。
A perfect shuffle type of free space optical intcrconnected multi-layer globally connected neural network module is firstly introduced.
首先介绍一种洗牌型自由空间光互连多层全互连神经网络模型。
In this paper, a multi layer template correlation neural network (MTCNN) based on the pipelined image processing structure is proposed for the recognition of lane mark.
本文提出了一种便于流水线图像处理结构实现的多层模板相关神经元网络(MTCNN)。
Mixed method was built to calculate the weights and thresholds of multi-layer neural network by utilize BP algorithm and terraced optimizations.
为确定多层人工神经网络的权值和阈值建立了混合求解方法，即迭代前期采用BP算法，而迭代后期采用梯度优化法进行计算。
Mixed method is built to calculate the weights and thresholds of multi-layer neural network by utilize BP algorithm and terraced optimizations.
为确定多层人工神经网络的权值和阈值建立了混合求解方法，即迭代前期采用BP算法而迭代后期采用梯度优化法进行计算。
Using the basic principle of analog parallel harmonics measurement and a special multi-layer feedforward neural network, a corresponding harmonics measurement on-line is built.
通过构造一个特殊的多层前向神经网络，利用模拟并行测量装置的基本原理，设计了相应的谐波监测电路。
This paper presents a kind of software faults prediction model based on artificial neural network and the structure of the feed-forward multi-layer network with backpropagation learning algorithm.
该文介绍了一种基于人工神经网络的软件失效预测模型，给出了基于反向传播算法的多层前向网络的网络结构。
The structure of multi-layer feedback forward neural network is optimized by improved PSO. Learning quality and training speed of the neural network are improved.
提出的自适应粒子群优化算法，用于优化多层前馈神经网络的拓扑结构，提高了神经网络的学习质量和速度。
In this paper, a new method to generate the texture image by use of Multi layer feed forward neural network is presented.
提出了一种利用多层前馈神经网络生成纹理图象的新方法。
Generally, it is difficult to determine in advance a suitable network structure when a multi layer perceptron neural networks is used for a special fault diagnosis problem.
一般对特定的基于多层感知器的故障诊断问题，很难确定神经网络的结构。
This paper presented particle swarm optimization (PSO) technique to train multi layer artificial neural network for predicting model of diameter errors of boring processes.
采用粒子群算法对镗孔加工尺寸误差人工神经网络预测模型进行优化。
A one-by-one learning algorithm for multi-layer neural network modelling is presented based on the back-propagation mechanism of network error.
基于误差反向传播的机制，针对连续制造过程的预测与控制，提出多层神经网络的逐个样本学习算法。
A one-by-one learning algorithm for multi-layer neural network modelling is presented based on the back-propagation mechanism of network error.
基于误差反向传播的机制，针对连续制造过程的预测与控制，提出多层神经网络的逐个样本学习算法。
应用推荐