- 更多网络例句与神经网络相关的网络例句 [注：此内容来源于网络，仅供参考]
-
Algorithm application of neural networks.Ⅲ Implementation of neuro-computers. The main contribution of the dissertation can be summarized as follows: 1 Hopf bifurcation of three kind of neural networks are discussed in detail, including type of discrete time delay, type of time delay with weak kernel and strong kernel as well as the proof of existence of bifurcation. Other problems such as asymptotic stability of bifurcation periodic solution, algorithm of determining the bifurcation direction, asymptotic stability and style of periodic solution are also studied. The average time delay is chosen as the bifurcation parameter, phenomena pertinent to system states of the continuous time delay network with strong kernel evolving from stable to oscillating, then back to stable again are observed.
论文的主要创新之处可以归纳如下： 1）针对目前国内外对神经网络的分岔研究较少的情况，论文中详细讨论了带离散时延神经网络、带弱核的连续时延神经网络、带连续分布时延且具有强核的神经网络的Hopf分岔现象，从理论上证明了Hopf分岔的存在性，并研究了分岔周期解的渐近稳定性，得到了确定周期解的渐近稳定性、分岔方向、周期解的渐近形式的算法；用平均时延作为分岔参数，发现带强核的连续时延神经网络中存在着系统的状态由稳定变化到振荡现象，当继续增加平均时延参数时，又从振荡变为稳定这一特殊的动力学现象。
-
Through above study, the theoretical analysis of the inherent fault tolerance of feed-forward neural networks has been extended from hard-limit activation functions to differentiable activation functions; 2. By using above method, fault tolerance of discrete Hopfield feedback neural networks have been also analyzed. It means that the above method can be applied not only for feed-forward neural networks but also for feedback neural networks; 3. For the feed-forward neural network with the Sigmoid activation function, Chebyshev Inequality method was presented.
这项研究将以前仅限于对硬限幅作用函数前向神经网络固有容错性能的理论分析推广到具有可微作用函数的前向神经网络； 2 针对离散型Hopfield反馈神经网络，利用上面提出的方法，对其同样进行了容错性分析，得出许多有用的结论和计算公式，说明上面提出的方法不仅适用于前向神经网络，同时也适用于反馈神经网络； 3 针对具有Sigmoid作用函数的前向神经网络提出了一种切比雪夫不等式法。
-
Proceed from the principle of neural networks, the mechanism of mapping between input and output of neural networks was analyzed, and the BP algorithm for training the thresholds of neurons was derived. Based on the study to the distinguishability of input of networks, the effect of neural networks to distinguish-ability of characteristics was studied, and the optimizations of the structure of networks, learning rate, impulse factor, thresholds of neurons and initial weight of networks were completed. Through the experiments under fixed cutting regime and alternative cutting regime, the methods based on neural networks for tool wear monitoring were studied.
本文从神经网络的基本原理出发，研究了神经网络输入输出的映射机理，探讨了神经网络处理方法具有自适应性的原因；推导了神经元阈值学习BP算法；在研究网络输入特征可分性准则和特征敏感性准则的基础上，探讨了神经网络对特征可分性的作用；完成对网络结构参数、网络学习率和冲量因子、神经元阈值以及网络初始权值等参数的优化；并在固定切削用量和变切削用量条件下，对基于神经网络的刀具磨损检测方法进行了实验研究。
-
At first, with the low-frequency data measured, three of the LRE fault detection systems for the real-time condition are proposed using the nonlinear identification technology of the BP neural network, the state estimation technology of the dynamic neural network, and the pattern recognition technology of the fuzzy hypersphere neural network. The learning algorithms of the BP and dynamic neural network are researched at the same time. Furthermore, while the engine operation is divided into the start and steady-state processes, the real time ability, the response time, the accuracy, the robustness, the sensitivity and the monitoring parameter optimization are studied. In the test data analyses of the YF-75 engine, the detection system correctly carried out for all normal tests, and in the three abnormal tests the engine faults were accurately forecasted.
首先，基于低频测量数据，采用BP神经网络的非线性辨识技术、动态神经网络的状态估计技术及模糊超球神经网络的模式识别技术，提出了三种发动机故障实时检测系统；同时研究了BP神经网络和动态神经网络的学习算法；另外还把发动机工作分为启动过程和稳态过程，分别讨论了神经网络故障检测系统的实时性、及时性、准确性、鲁棒性、敏感性及参数优化问题；在YF-75发动机试车数据分析中，不仅全部正确地监测了正常试车过程，而且准确地预报了三次异常试车中的发动机故障。
-
For the data set with noises, a regularization intropolation method is proposed according to regularization theory. The relation between the regularization intropolation method and radial basis function method is analysed and structure of regularization neural networks is proposed. RBF neural network is introduced by mortifying the regularization neural networks. Finally the approximation capacity of RBF neural networks is analysed. 4. A method of selecting the centers of hidden layer neurons of RBF neural networks is proposed.
首先从精确内插问题开始对RBF神经网络进行讨论，然后根据正则化理论提出了在数据集带有噪声的情况下的内插方法，并分析了这种内插方法和径向基函数方法之间的密切联系以及其对应的正则化神经网络结构，其次对正则化神经网络进行了修改，得到正则化神经网络的简化形式—RBF神经网络，最后分析了RBF神经网络的逼近性能。
-
First, the traffic flow time series chaotic feature is extracted by chaos theory. pretreatment for traffic flow time series, and the wavelet neural networks model was build by this. Second, the chaotic mechanism and the chaotic probability is described. Based on chaotic learning algorithm, and the wavelet neural networks fast learning algorithm of traffic flow time series is designed based on chaotic algorithm. Last, a single-step and multi-step prediction of traffic flow chaotic time series is researched by BP neural networks, wavelet neural networks and wavelet neural networks based on chaotic algorithm. The results showed that the wavelet neural networks predictive performance is better than the BP networks and the wavelet neural networks by the simulation results and root-mean-square value.
首先，通过混沌理论提取了交通流量时间序列的混沌特征，并在此基础上建立了小波神经网络交通流量时间序列模型；接着，阐述了混沌学习算法的混沌机理、混沌产生的概率，设计了基于混沌算法的小波神经网络交通流量混沌时间序列快速学习算法；最后利用交通流量混沌时间序列对BP网络、非混沌算法的小波神经网络以及基于混沌算法的小波神经网络进行了单步预测和多步预测，并对预测结果的仿真图和真实值与预测值的方均根进行了比较，结果表明基于混沌学习算法的小波神经网络的预测性能明显优于应用BP网络和非混沌算法的小波神经网络。
-
The uniform approximation of normal wavelet neural network and the robust analysis of wavelet neural networks of the combination of Sigmoid function are detailedly introduction; Multiple model failure detection based on wavelet neural network is demonstrated detailedly; At last, the failure diagnosis results of aerocraft is present seperately by employing wavelet neural network and BP neural network, and the fault diagnosis of areocraft system by wavelet neural network is achieved.
论文以小波神经网络为研究对象，提出了一类新的加权小波基，分析证明了加权小波基的诸多良好特性；对于常见小波神经网络的一致逼近特性、S型函数组合小波神经网络的鲁棒性分析、多模型小波神经网络的故障检测等问题给出了详细的论证；最后，针对歼击机的常见故障问题，分别给出了应用小波神经网络和BP神经网络的故障诊断结果，实现了小波神经网络对飞机系统的故障诊断。
-
The design of transplanter for rice growing in cupulate tray is the critical link in rice growing in cupulate tray technology,the design method is not mature,for exploring a new design method,having discussed neural network s serviceability in agriculture machinery mechanism design with the theoretical basis of self-organizing feature mapand the back-propagation network,the integrated SOM-BP nerve network model is applied in the field of transplanter s critical mechanism design for rice growing,al...
水稻钵育栽植机的设计是实现水稻钵育栽培技术的关键环节，区别于传统的水稻栽植机其关键部件的设计方法还不成熟，在理论研究方面还不完善。为探索新的设计方法，论述了神经网络算法对农业机械设计的适用性，以自组织特征映射网络SOM 和误差反向传播网络BP为理论基础，将SOM-BP集成神经网络模型应用于水稻钵育栽植机关键部件设计领域，建立神经网络模型，通过集成网络训练，得到设计结果。验证了SOM-BP神经网络在农业机械机设计中的正确性和精确性。
-
Three kinds of arm's robust control theorys are designed: the torque control based on FNN controller, the computed torque control with sliding mode compensation and the computed torque control with WNN compensation. FNN syncretizes the reasoning ability of fuzzy control and parameters' self-learning ability of neural networks. It does not depend on the precision of the mathematical model, and can overcome the impact of the uncertainty effectively. So FNN is regarded as the manipulator controller and used to the trajectory tracking of arm control. The computed torque control with sliding mode compensation is designed.
在此基础上，研究了机械手臂的鲁棒控制法，分别设计了基于模糊神经网络的机械手臂力矩控制方法、基于滑模变结构控制补偿的机械手臂力矩控制方法以及基于小波神经网络补偿的机械手臂力矩控制方法，具体内容如下：模糊神经网络融合了模糊控制的推理能力和神经网络的参数自学习能力，它不依赖于对象精确的数学模型，能有效地克服被控对象存在的不确定部分的影响，本文把模糊神经网络作为机械手臂的关节伺服控制器，通过对网络参数的学习训练来调整机械手臂关节的控制力矩，实现对机械手臂的轨迹跟踪控制。
-
The research of neural network realization can be traced back to 60's. It processes along with two avenues: fully hardware realization and virtual realization. Scientists have developed many neurochips supporting fully hardware realization. Neurocomputing simulating supporting environments, neurocomputing accelerators and parallel neurocomputing systems also have been developed for virtual realization of neural network.
神经网络实现技术的研究可以追朔到六十年代，该项研究一直是沿两个方向开展，即神经网络的全硬件实现和神经网络的虚拟实现，科学加们也研制出了许多支持神经网络全硬件实现的神经芯片，以及支持神经网络虚拟实现的各种神经计算软件模拟环境、加速器和并行神经计算机系统。
- 更多网络解释与神经网络相关的网络解释 [注：此内容来源于网络，仅供参考]
-
Ann：人工神经网络
这部机器里面使用了叫做"人工神经网络"(ANN)的技术,机器学习飞行的过程叫做"训练". 由一个有经验的专业航模运动员使用遥控器操作这架飞机做出各种特技动作. 机器仔细观察自己每时每刻的位置与姿态,
-
nerve net：神经网络
周围神经:peripheral nerve | 神经网络:Nerve net | 肋间臂神经:Intercostobrachial nerve
-
BP nerve net：神经网络
副神经:accessory nerve | 神经网络:BP nerve net | 神经重建:corneal nerve regeneration
-
nerve net self-adapting controller：神经网络自适应控制
数值不稳定现象:Numerical instability phenomena | 神经网络自适应控制:Nerve net self-adapting controller | 交流伺服系统:nerve net self-adapting controller
-
nerve net self-adapting control：神经网络自适应控制
交流伺服系统:nerve net self-adapting controller | 神经网络自适应控制:nerve net self-adapting control | 参数自适应模糊PID:Self-adapting fuzzy PID
-
Neural Networks：神经网络
瑟热基的研究组侧重于通过两种方式来实现"行为基础控制":一个是"模糊逻辑"(fuzzy logic),另一个是"神经网络"(neural networks). 在这两个系统之间最主要区别在于,应用"模糊逻辑"的机器人通过现成的、不能丰富更新的知识来完成任务,
-
NN：神经网络
[关键词]汽油机 暂态燃油补偿(TFC) 神经网络(NN)[摘要]通过对三种暂态燃油补偿模型(TFC)的剖析,并在相同条件下对每个模型进行仿真,提出了基于模型的TFC和基于神经网络(NN)时,模型选取的方法和需要考虑的问题.
-
Topological Structure Enciphering：人工神经网络
拓扑遍历混合:topological ergodic mixing | 人工神经网络:Topological Structure Enciphering | 网络拓扑结构:Network Topological Structure
-
neuronic network：神经网络
neurocomputer 神经计算机 | neuronic network 神经网络 | neutral zone 无控制酌的参数范围
-
INNS InternationalNeuralNetworkSociety：国际神经网络协会
INND InternetNewsDaemon 因特网新闻后台程序 | INNS InternationalNeuralNetworkSociety 国际神经网络协会 | INOC InternetNetworkOperationCenter 因特网网络操作中心