神经网络结构

该算法框架具有较强的通用性，适合于TSP、顶点着色问题、Job-shop调度问题、神经网络结构优化问题、系统建模等一大类非数值优化问题。

This algorithm is all-purpose and it is fitted for traveling salesman problem , job-shop scheduling , vertex coloring problem , the optimization of the artificial neural network architecture and Modeling for Systems , etc.

研究适用于隐马尔可夫模型（HMM）结合多层感知器（MLP）的小词汇量混合语音识别系统的一种简化神经网络结构。

A simplified neural network architecture is presented . It is applicable to any small vocabulary hybrid speech recognition system that combines hidden Markov model ( HMM ) with multi-layer perceptron ( MLP ) .

BP神经网络结构与样本训练参数选取的初步探讨

Discussion about BP Neural Network Structure and Selection of Samples Training Parameters

对BP神经网络结构及BP算法进行了研究。

The thesis studies on BP Neural Network 's structure and BP algorithm .

神经网络结构分析与BP算法修正

Neural network structure analysis and BP algorithm modification

润滑油智能分析系统中BP神经网络结构的设计

Application of Genetic Algorithm in the BP Neural Network Structure Design of Intelligence Analysis System of Lubricated Oil

基于MDL的RBF神经网络结构和参数的学习

Learning the architectures and parameters of RBF neural network based on MDL

文章的最后，对BP算法的并行实现进行了分析，理论分析结果显示，多种神经网络结构都可有效地并行化。

An analysis of the parallel implementation of the BP algorithm is also presented . The theoretical analytic expressions show that the parallelization is efficient for many network architectures .

首先提出一种基于Agent封装的模糊神经网络结构，它能主动发现服务并进行自发互操作，多Agent之间能相互协调和协同工作；

A kind of new belief measure structure , called fuzzy-neural network structure under the encapsulation of agent is presented , which can discover service proactively and supply spontaneous interoperation in cooperation with multi-agents .

根据引信贮存可靠性的特点和BP神经网络结构，建立了引信贮存可靠性预计的神经网络模型；

In this paper , a neural network model is given for the reliability prediction of fuze storage according to the feature of the fuze storage reliability and the architecture of BP neural network .

在瑕疵分类方面，本文采用了基于前馈神经网络结构式（BP）的自学习算法，实验结果表明，这种方法可以有效地提高分类效果，使之符合用户的需求。

To classify the defects effectively , a novel learning method based on BP is employed . Experiments shows that the proposed approach efficiently improves the result of classifying and well fulfills the users requirement .

由于它采用全互连神经网络结构，易于并行计算和VLSI实现，从而可满足军事上实时处理的需要。

Owing to adopting network structure , the algorithm is prone to parallel computation and VLSI design , and consequently can satisfy real time military processing needs .

RBF网络模拟人脑中局部调整和相互覆盖接收域的神经网络结构，是一种局部逼近网络，它可以以任意精度逼进任意连续函数。

RBF network is a structural simulation of local regularization and mutual overcast in human brain . With local approximation characterize , it can approximate arbitrary continuous function with arbitrary precision .

随后确定了BP神经网络结构的层数（输入层、输出层、隐层）和各层的节点数，从而完成了BP神经网络结构模型的设计。

Then determine the structure of BP neural network layer ( the input layer , hidden layer and output layer , each layer ) the number of nodes , thereby completing the structure of BP neural network model design .

本文针对以上问题提出一种依据测量数据自动获取模糊规则的方法，并给出了一种能够有效描述模糊规则可解释性的模糊RBF神经网络结构。

This thesis aimed at above problems puts forward an approach of fuzzy rules automatic extraction according as measure data and propose a RBF net structure , which can be good for description the fuzzy rule interpretable characteristic .

讨论了动态神经网络结构及其算法，然后利用所设计的动态神经网络对杜芬（Duffing）方程和一实际结构在不同输入条件下的响应进行预测。

This paper discusses the structure and algorithm of dynamic neural network , and use this dynamic network to predict the response of Duffing equation and a real structure in different input conditions .

提出了一种直接控制的自适应神经元模型和神经网络结构，以及一种快速学习算法（FLA），并把该神经网络和算法用于驼峰速度控制系统。

A class of neural networks containing direct controlled adaptive neuron and the corresponding fast learning algorithm method are proposed for developing this new humping speed control system .

仿真结果表明，由于系统参数得到调整，对于同一问题，改进IPL算法得到的径向基神经网络结构较一般算法得到的网络结构简单，输出结果也较为精确。

The simulation results showed that the new algorithm can induce a simpler network structure than the former algorithm , and the output of the new IPL inducing network is more accurate than before .

前端采用3层BP神经网络结构，以传感器接收数据为输入，以神经网络输出作为证据，后端对不同传感器的证据按D-S理论进行融合，得到待识别目标的识别概率。

Firstly , adopt 3 layer neural networks , data of sensor as input of neural networks , output of neural networks as evidence , secondly , according to D-S theory to fuse the evidences of different sensors , finally , obtaining probability of recognition to aircraft .

采用MLP实现MCE训练中的分类损失计算，从而将MCE训练过程与MLP分类器设计统一在一个神经网络结构中，通过BP算法予以实现。

This paper proposed that the classification losses are calculated by multi-layer perceptrons in MCE training . So , MCE training can be incorporated with MLP classifier design in an integrated neural network structure , and realized by means of an effective error back-propagation ( BP ) algorithm .

用于大工业过程建模的新型小波神经网络结构

New architecture of wavelet neural network for modeling large-scale industrial processes

一种新型模糊神经网络结构确定的研究

Study on Determination of the Structure of an Improved Fuzzy-Neural Network

混合语音识别系统的一种新的简化神经网络结构

A Simplified Neural Network Architecture for a Hybrid Speech Recognition System

单刚矩阵计算用神经网络结构的实验确定

Experimental Determination of the Structure of NN for Stiffness Matrix Computation

模糊聚类分析在模糊神经网络结构优化中的应用

Fuzzy Clustering Analysis for Optimizing the Structure of Fuzzy Neural Network

基于神经网络结构学习的知识求精方法

A knowledge base refinement method based on structural learning of neural networks

基于样本曲率的模糊神经网络结构学习算法

Samples Curvature Based Algorithm for Fuzzy Neural Network Structure Learning

多输入模糊神经网络结构优化的快速算法

Fast Learning Algorithm of Small Multi-input Fuzzy Neural Network Structure

径向基函数神经网络结构的混合优化策略

Hybrid optimization strategy for radial basis function neural network structure

为此提出了一个适合于重复作业应用的分布式神经网络结构。

A distributed neural network structure along a demonstrated trajectory is proposed .