查询词典 neural network

In all, this article has made thorough study in the optimal combination of modular neural networks, predisposal of fingerprints, extraction of features and identification of characters and fingerprints based on neural network.

概括起来，本文在模块化神经网络最优组合、指纹的预处理、特征提取以及基于神经网络的指纹识别等方面进行了较为深入详细的研究。

The multi neural networks ensemble algorithm was primary discussed and studied, A neural network ensemble algorithm used in automatic target recognition is proposed,.

5对多神经网络集成算法进行了初步的探讨研究，给出了一种用于自动目标识别的神经网络集成算法，并结合算法设计了一个基于多CPU并行结构的多目标识别神经网络系统。

It has been observed that pyrocatechol and m-phenylenediamin can sensitively inhibit the discoloration of neutral red oxidation by the H2O2 and in the presence of catalyzer Fe in dilute sulfuric acid solution but the inhibitory effects of two organic compounds can not be added. Based on this research, the advantages of artificial neural network were adopted to handle the experimental data and a new inhibitory kinetic spectrophotometry of simultaneous determination for pyrocatechol and m-phenylenediamin with artificial neural networks was established.

在硫酸性介质中，Fe能够催化H2O2氧化中性红褪色反应，邻苯二酚和间苯二胺都能阻抑该催化氧化褪色反应的速度，研究发现：两者对Fe催化H2O2氧化中性红褪色反应阻抑作用不具有加和性，根据这一现象，用人工神经网络处理非线性体系的优势进行数据处理，从而建立了一种新的测定邻苯二酚和间苯二胺混合物的人工神经网络阻抑动力学光度法。

In this paper, the forecast model of scouring depth is conducted by neural network and BP neural networks.

利用神经网络和一些实测数据建立BP神经网络模型，进行冲刷深度的预测，用收集到的桥墩局部冲刷数据样本训练并测试BP神经网络模型。

At last, the application of above modeling and control strategies has been demonstrated by the simulations of a nonlinear dc motor control problem. Under this control strategy, system identification phase is not needed, and only a controller based on the recurrent neural network is provided. Because the control and learning laws are designed with stable theory, stability and convergence problems are solved here with rigorous analysis, which can not been analyzed easily when usual BP neural networks are used.

最后通过非线性电机模型的仿真研究，表明了基于上述动态动态递归神经网络模型对非线性系统进行自适应控制的实际可行性，并且采用这种方法不需要对系统进行离线辨识，整个系统只采用了一个基于动态递归神经网络的控制器，由于整个系统是基于稳定性理论设计的，有效地解决了应用BP网络等其它前向网络时系统的稳定性和收敛性难以分析的问题。

Focusing on the disadvantages in the BP neural network such as low convergence rate,easily falling into local minimum point and weak global search capability,a new method that used GA to train BP neural networks to gain best weights was presented.

针对传统的BP算法存在收敛速度比较慢、容易陷入局部极小值以及全局搜索能力弱等缺陷，提出了神经网络与遗传算法。结合的方法，采用遗传算法。练BP神经网络，优化网络权值。

The digital closed-loop control system is designed and the dissolutive oxygen control algorithm is given out using neural PID algorithm. The traditional PID algorithm is optimized by neural network cell method and the weight value of NNC is generated on-line.

设计了全数字化的闭环控制系统，以溶解氧指标为控制对象进行了控制算法设计，针对转刷曝气工艺的特点，采用神经PID调节算法，引入了线性神经元对经典PID算法进行优化、应用梯度下降法对NNC网络权值进行在线计算。

This paper explored a new method using H-H spike neural network model,circle mapping and symbol-dynamics theory which is a simulator designed for modeling the Echolocation function of biosonar neural system based on measuring the interaural time difference .

本文尝试结合H-H神经元模型和基于圆映射的处理方式在序空间设计一个生物神经计算模型模拟生物声纳系统依靠声波到达双耳的相位差信息来得到声源方位信息的功能。

Based on the spaceflight technology innovation program of"Research on the Testing Method of Reliability----Research on the Fault Diagnostic Expert System and Neural Network"and the Pre-Research Defense Projects of"Research on longevous service and high reliability of Satellites"of the National tenth-five-year plan, taking attitude control system of a satellite as object, the theories and the applications of the neural networks and expert system in the fault diagnosis are studied in this dissertation.

本文以航天技术创新基金项目&可靠性试验方法研究——故障诊断的专家系统神经网络技术研究&和国家武器装备&十五&预研项目&卫星长寿命高可靠性技术&为背景，以卫星姿态控制系统为研究对象，在理论和实践两个方面对神经网络和专家系统相结合的故障诊断技术及其在卫星中的应用进行了研究。

The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radices as the stimulant function. The idiographic algorithm was presented. It can combine the advantages of wavelet analysis and neural networks.

以非线性Morlet小波基作为激励函数，形成神经元，结合小波变换与神经网络各自的优点，建立集小波分析与神经网络于一体的紧致型小波神经网络，并给出了具体的算法。

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。