在一类随机神经网络的研究中，一些研究人员提出马尔科夫神经网络模型。
In studying of a class of random neural network, some of relative researchers have proposed Markov model of neural network.
提出了一种利用前馈随机神经网络在分组网络中进行实时语音质量评价的新方法。
A novel approach to the real-time speech quality evaluation in a packet network using feed-forward multiple class random neural network (FFMCRNN) was presented.
本文提出了一种结合随机神经网络与运动矢量的新方法，并使用它对人眼视觉退化感知进行估计。
We propose a new method using artificial random neural networks (RNNs) with motion evaluation as an estimation of perceived visual distortion.
作为仿生神经元数学模型，随机神经网络在联想记忆、图像处理、组合优化问题上都显示出较强的优势。
As a biological neural mathematical model, RNN has particular advantages of associative memory, image processing and combinatorial optimization.
根据该理论，学习过程就是由随机信息源产生的输入信号驱动神经网络参数不断修改的过程；
The learning process of a neural network is considered the process in which neural network variables are changed with a time series of input signals generated from a stochastic information source.
研究了一类随机变时滞递归神经网络的几乎指数稳定性问题。
The almost surely exponential stability of stochastic recurrent neural networks with time-varying delays is investigated.
实例结果表明时间序列经模糊滑动平均处理后，随机波动对神经网络预测精度的影响可大大减小。
A fuzzy preprocessing method. that is. fuzzy sliding averaging. is Proposed to decrease the influence of random, an example shows the improvement of the forecasting neural network.
利用改进的BP算法，结合电波传播理论，建立了随机雨介质的等效复折射指数的神经网络模型。
The neural network model of the equivalent complex refractive of random rain media is developed by means of the improved BP algorithm, based on the electromagnetic wave propagation theory.
本文通过检测电流信号基于随机模糊神经网络建立了刀具磨损量的软测量模型。
Through measuring the electric current signal, the soft sensing model used for tool wear estimation based on stochastic fuzzy neural network(SFNN) is presented in this paper.
应用神经网络对未建模型的非线性随机系统进行控制。
Use Neural Network to control unfounded model nonlinear random system.
通过检验发现神经网络预测模型在预测精度上要高于随机游动模型，而且两个模型的预测结果存在明显的差异。
Through the test we found that the forecast accuracy of neural network forecasting model is higher than that of random walk model, and there is an obvious difference between two models.
利用人工神经网络技术，提出预报离散随机的电离层骚扰事件的新方案。
A new method for predicting disturbances in the ionosphere by using the Artificial Neural Network (ANN) has been presented.
仿真实验表明，基于多步预测的PID型神经网络控制系统能有效抑制随机干扰，具有较强的适应性和鲁棒性。
Simulation res ults prove that this new multi-step prediction based on PID-like neural network control system can effectively attenuate random noise interference and is more robust and adaptive.
经对性能指标性质的分析给出了一种模糊神经网络的学习算法——二阶段变半径随机搜索法。
Based on the analysis of the performance index a new algorithm, two stage random search algorithm with variable radius, is put forward.
本文指出和讨论了人工神经网络方法在处理某类随机性问题上存在着的潜力。
Potentiality of artificial neural network method in copping with a kind of random problem is shown and discussed.
本文分析了随机数据分布的识别方法，并提出了基于神经网络的随机数据分布的识别方法。
In this paper, the approaches for recognizing distribution of random data are discussed, and a new approach based on neural network is presented.
人工神经网络时序模型开辟了随机模拟法在设计洪水计算中应用研究的新途径。
Artificial neural network series models break a new approach for stochastic modeling in computing design flood.
研究了大跨空间结构脉动风荷载的随机模拟技术，基于神经网络进行了风速时程的随机模拟。
The random simulation of dynamic wind load for large-span structures is studied. Wind speed processes based on artificial neural networks are generated.
针对模糊综合评判法主观性强，随机性大的缺点，引入模糊神经网络算法对其加以改进。
Because of the fuzzy comprehensive evaluation has subjective and random, we introduce the neural network to improve risk assessment model.
采用在已知参数范围内随机选取足够的样本的方法来训练危险度分级的神经网络模型。
The ANN model of the dangerous degree classification also trained by random selected enough samples in the range of known parameters.
金融时间序列具有很强的随机性和非线性性，而神经网络具有良好的非线性映射能力及自适应、自学习和良好的泛化能力，因此非常适合处理金融时间序列这样的数据。
Financial time series has high randomicity and nonlinearity. Neural network is quite suitable in the process of financial time series data for its good ability of nonlinear mapping and generalization.
还指出由于当前的连续小波神经网络主要使用传统BP神经网络的随机初始化方法和基于梯度的训练算法，因此存在收敛性差的缺点。
It is also indicated that current WNN has a poor convergence performance because of adopting the random initialization method and gradient training algorithm of traditional BP NET.
针对汽轮发电机组振动振幅受运行参数及随机因素影响的特点，提出了用人工神经网络中的递推合成BP网络对汽轮机的振动故障进行多因素预测。
Vibration amplitude of steam turbine is affected by operation parameters and random factors, the paper Contributes a Prediction method using multifactor model of recurrent combined BP networks.
方法：应用BP神经网络模型，分析32例肝癌病例DSA影像资料数据，建立计算机临床辅助诊断模型，然后把100个随机抽样测试样本输入模型验证。
Methods: the 32 cases of DSA image data are analysed, the BP Neural Network is used to build diagnostic model, we input 100 cases of random samples to verify the model.
考虑到随机因素及时滞对神经网络系统的稳定性的影响，这使得研究随机时滞神经网络的稳定性具有深远意义。
The impact of stochastic factor and delay on stability of the neural network is significant to investigate the stability of stochastic neural network with delay.
根据影响道路交通环境的各单项评价指标及其分级标准，利用随机分布理论生成足够多用于神经网络建模的样本数据。
According to the road traffic environmental quality evaluation indexes and their grade standards, efficient samples based on the random-distribution theory were produced.
根据影响道路交通环境的各单项评价指标及其分级标准，利用随机分布理论生成足够多用于神经网络建模的样本数据。
According to the road traffic environmental quality evaluation indexes and their grade standards, efficient samples based on the random-distribution theory were produced.
应用推荐