- 更多网络例句与多层神经网络相关的网络例句 [注：此内容来源于网络，仅供参考]
-
Several strong results on neural network approximation capability obtained in this dissertation are important in the approximation theory and applications of neural networks.
本文系统地研究了多层神经网络的非线性逼近能力，给出了多层网络可一致逼近有限维空间R〓紧集上的连续函数、无穷维函数空间紧集上的连续泛函和连续算子以及布尔函数的理论证明。
-
This paper makes use of improved BP algorithm compared to the traditional one and the new algorithm brings us higher speed in constringency and more preciseion in detection.
BP学习算法是神经网络中的一种重要的方法，反向传播网络是典型的前馈型网络，结构上它属于多层网络，分为输入层、隐层和输出层
-
Applications to multilayer neural network learning show that the new algorithm is more efficient and accurate than BP, DFP, and BFGS algorithms.
在多层神经网络训练中的应用表明，它比普通BP学习算法、DFP和BFGS方法更有效、更准确。
-
In this dissertation, the structure of MFNN and a training algorithm which can be easily implemented in hardware for a class of neural networks with general topology, are studied. Furthermore, the application of the redial basis function network, which can be classified as a type of MFNN, in the design of sliding mode controller is also investigated.
本文研究了多层前馈神经网络的结构问题和一种易于硬件实现的学习算法，还讨论了可以划为多层前馈神经网络的RBF网络在滑模控制器设计中的应用。
-
Based on the ability of neural network in classification and recognization, a feed-forward multi-layer neural network is applied in the diagnosis of adhesive bond quality between metallic and nonmetallic components of a pressure vessel through acoustic feature extraction in the frequency domain, based upon the acoustic response on knocking the pressure vessel.
本文基于神经网络对目标的识别与分类能力，用简单的敲击法获取了某压力容器的声响应信号，通过对声信号的频域特征提取，应用前馈多层神经网络对压力容器的金属与非金属部件之间的粘接质量进行了诊断。
-
Prediction of self-ignition duration of coal with feedforward multi-layer artificial neural network.
采用前向多层神经网络预测煤的自然发火期。
-
The problem of using thermocouple is introduced, and different methods of building mathematical model of thermocouple characteristic are discussed.
简单介绍了当前热电偶应用存在的问题，分析了建立热电偶特性的数学模型的各种方法，并提出了应用前向多层神经网络建立热电偶特性数学模型的方法及其优势。
-
BP neural network based on adaptive UKF is introduced in this paper for the standard BP neural network has slow converges,local minimum value and weak generalization ability.It can train weight of BP and improve the efficiency of BP without linearization by using the frame of Kalman filters and adaptive factor to adjust the variance of dynamic model.
1引言1986年，Rum elhart和M cC lelland等人在多层前向神经网络模型的基础上，提出了误差反向传播学习算法(BackPropagation简写BP)，该算法是目前在神经网络中应用最广泛的算法，它解决了多层前向神经网络的学习问题[1]。
-
A non-uniformly windowed pyramidical architecture is proposed, the normalizations of the feature vectors of two extraction algorithms are investgated and the Polak-Ribiere learning algorithm is modified to guarantee the weight vector not to converge to non-stable local minima.
文中提出了一种带非均匀窗形式的金字塔状多层神经网络模型I研究了两种特征提取方法的向量规整问题，改进了Polak—Rjbiere学习算法并证明它能够保证连结权向量不收敛到非稳定局部极小点。
-
In Chapter 2, the learning algorithm of the single-layer perceptron and its limitation are considered firstly.
前馈结构的神经网络是最重要的神经网络模型之一，本文系统地研究了前馈结构神经网络的能力，包括多层感知机和径向基函数网络两部份。
- 更多网络解释与多层神经网络相关的网络解释 [注：此内容来源于网络，仅供参考]
-
std：标准差
经过对试验数据的多次仿真试验,我们提取到其故障特征信号为峰值(MAX)、峭度(KUR)、标 准差(STD)这三个量作为网络的输入. 网络采用离线训练、在线使用的方式. 神经网络的结构如图3所示,其中隐含层神经元个数、各个神经元上的权值和阈值均由大量试验样本数据训练得到.
-
polytrope：多层球
多层高楼high-rise | 多层球polytrope | 多层神经网络multilayer