查询词典 neural network

At the recognition stage, we propose the combination of characteristic input and Multi-layer Perception Network, which both reduces information input and improves self-study and fault tolerance of artificial neural network, resulting in a more precise recognition.

在识别阶段，本文采取特征提取和多层感知器网络相结合的识别方法，既可以有效减少信息量的输入，又充分发挥了神经网络的学习和容错能力，从而达到较高的识别精度。

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。

Genetic-based fuzzy neural network is used to fuse a lot of data of information handling unit, and the method of using Genetic Algorithm to optimize general network parameter and using BP Algorithm to modulate and optimize local parameter is presented.

采用基于遗传算法的模糊神经网络对信息处理单元的大量数据进行数据融合，提出了采用遗传算法优化具有全局性的网络参数，用BP算法调节和优化具有局部性的参数。

Transformer; magnetizing inrush current; fault current; BP neural network; RBF network

变压器；励磁涌流；故障电流； BP神经网络； RBF神经网络

The Back-Propagation network is one of the most useful Artificial Neural Network, which can deal with complicated data and nonlinear problem.

BP网络是最具有代表性的人工神经网络之一，具有强大的数据处理能力和非线性映射能力。

Direct difference is sensitive to noisy data, so a threshold limitation is given, which can not only filter the result from noisy data but also pick edge points up according men's desire. On the other hand, artificial intelligence is used for segmentation in reverse engineering. Because the essence of segmentation is clustering similar characteristics and self-organizing feature mapping is one function of neural network, SOFM network is used for segmentation in the thesis, coordinates and normal of data points is took as the characteristics vector.

第二种方法，基于双向角度微分的边点提取法，针对三维正交模型采用基于截面线的方式组织数据，此方法比基于曲率半径方法更简洁，不用进行曲面拟合，大大提高了计算速度；计算过程中由数据点的直接差分逼近微分，但直接差分对数据误差敏感，为此，本文提出了阈值过滤的方法，一方面过滤了数据误差在计算结果中引起的噪音，另一方面可以按照设计意图控制边点的提取；来决定是否提取光滑交接的边点。

First local surrounding-line integral bispectrum feature is extracted from the bispectrum of one dimensional range profile of space target, then BP neural network is used for target identification so that the network weights will not be the local lowest value.

提出了基于局部围线积分双谱的空间目标识别算法，从空间目标距离像的双谱中提取出局部围线积分双谱特征。

The simulation results show the good performance for the system by using network to adjust the parameters and the recurrent weight of neural network on-line dynamically on the condition of variety of system parameter and the impact of outside uncertainty factors.

仿真结果表明，当系统参数动态变化或受到外部不确定因素影响时，利用神经网络来在线调整网络的隶属函数参数以及神经网络递归权值，使系统具有良好的动、静态性能。

Based on expansion radial basis function network, one kind of new dynamic fuzzy neural network algorithm was proposed.

提出了一种新型的动态模糊神经网络算法，该动态模糊神经网络的结构基于扩展的径向基网络。

Hydraulic servo-system Fault detection Dynamic neural network Output recurrent network

液压伺服系统；故障检测；动态神经网络；输出递归网络

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。