神经式网络

This paper presents a new successive approximation nonlinear analog-to-digital converter based on feedforward neural network.

本文提出一种基于前向神经网络的逐次逼近式非线性A／D转换器。

In the first chapter, we introduce the research background and the basic task of this project.

论文第一章主要介绍了课题的研究背景与意义以及基本任务；第二章分析了当前COD测量技术与仪器的现状与特点，并提出了紫外扫描式多光谱COD测量技术；第三章详细介绍了系统的整体结构、光路扫描系统与硬件控制系统；第四章介绍了嵌入式系统的概念、特点，以及软件设计的流程、功能模块与调试分析；第五章介绍了神经网络的概念、建模与实验数据分析；第六章对课题进行了总结与展望，提出了改进的意见。

Based on neural network of capacitive pressure sensor nonlinear correction.

基于神经网络的电容式压力传感器非线性校正。

It turns the problem of differential game into the problem of maneuver identification and optimization control based on neural networks.

阐述了微分对策理论在实际应用中存在的问题，并从动态冲突的实际过程出发，将神经网络理论与分层式智能控制理论相结合，来模型化微分对策问题。

The experimental results show that temperature error and non-linearity of silicon piezoresistive pressure sensor can be reduced markedly.

本文针对其缺点，提出了以正交的局部函数——小波函数作为激励函数的小波神经网络对硅压阻式压力传感器的温度误差进行补偿。

Studies on the tautologies in some lattice valued logic systems and formula computation by means of neural net works.(1) Tautologies play a significant role in logic applications.

二、一类格值逻辑系统中的重言式和逻辑公式的神经网络计算 1、重言式在逻辑系统的应用中起着重要的作用。

Using RBF neural network substitutes BP network as the approximation of implicit performance function, and the response surface is formed in the sphere of hyper-pyramid at iteration step.

采用径向基函数神经网络，代替目前常用的BP网络，迭代过程中在超锥体的范围内构造响应面，逼近隐式的非线性功能函数。

On the basis of the orthogonal experimental design technique, I redefine the crossover operator, an important operator used in a genetic algorithm.

神经网络的训练过程和网络结构的寻优过程都是十分耗费时间的，为了寻找解决这个难题的方法，我尝试利用DSP/PC机组成的典型的主从式系统来实现自己提出的网络设计方法。

On the basis of the data obtained from the cam-type plastometer, four prediction models including the BP, Elman, RBF and GRNN neural network prediction models were established, which corresponded to the relationship between the deformation stress of nickel-chrome steel with chemistry elements, temperature, strain rate and deformation strain of the steel respectively. A comparative analysis for the prediction accuracy of the four models was obtained.

以凸轮式高速形变试验机进行的热模拟压缩实验得到的实验数据为基础，建立了热轧铬镍钢的变形阻力与其化学成分、变形温度、变形速度及变形程度对应关系的BP、Elman、RBF和GRNN 4种神经网络预测模型；并对4种网络的训练过程和预测精度进行比较分析。

This paper presents a N-R method of acquiring multi-level reasoning production rules automatically based on NN, so as to resolve the bottle neckproblem in building a knowledge - based system-knowledge acquisition. This methodadopts a characteristic NN structure model and corresponding learning algorithm, so thatN -R method can fix the number of hidden nodes dynamically and form new conceptswhich are not defined in the sample set in the course of learning. Having been trained, NNis transforme...

本文为解决知识系统构造过程中的瓶颈问题──知识获取，提出了一种基于神经网络NN的自动获取多级推理产生式规则的N－R方法，该方法采用了特有的NN结构模型和相应的学习算法，使得NN在学习过程中动态确定隐层节点数的同时，也产生了样例集中没有定义的新概念，学习后的NN能用本文提出的转换算法转换成推理网络，最终方便地得到产生式规则集

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。