将单层线性前馈网络用于矩阵求逆的方法,应用于电力系统故障计算中,从而简化了计算。
The linear forward feedback perceptron with single layer is used to seek the inverse matrix in failure analysis of power system, so that the calculation is simplified.
当训练样本线性可分时,本文证明前馈神经网络的在线BP算法是有限次收敛的。
In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.
本文结合岩体质量的模式识别,阐述了半线性前馈神经网络的基本原理和应用,并给出了其部分试验结果。
In this paper, the principle and application of semilinear feedforward neural network are described, some experimental results are also presented.
前馈神经网络由于具有理论上逼近任意非线性连续映射的能力,因而非常适合于非线性系统建模及构成自适应控制。
Because the feedforward neural network has an ability of approach to arbitrary nonlinear mapping, it can be used effectively in the modeling and controlling of nonlinear system.
基于输出层函数为线性函数的三层前馈神经网络,结合自适应步长和动量解耦的伪牛顿算法及迭代最小二乘法导出了一种混合算法。
On the basis of both adaptive BP algorithm and Newtons method, Quasi Newton algorithm with adaptive decoupled step and momentum (QNADSM) for feed-forward neural networks is derived.
讨论了利用仅含一个隐层的前馈多层神经网络来辨识离散时间非线性动态系统时的模型检验问题。
This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.
对线性网络的模型选择和多层前馈网络的关系做了细致的研究,并分别进行了仿真。
A delicate research about the relationship of the selection of model of the linear network part and the multi-layered feed-forward network part and simulation are presented.
一个简单的三层BP前馈网络,采用简单的非线性转移函数,就可以以任意精度逼近任何非线性函数。
A simple three-layer BP network using simple nonlinear transfer functions can approximate any nonlinear functions with any precision.
在点状激光三维扫描技术中,用线阵CCD采集深度坐标,用前馈型人工神经网络对深度坐标进行非线性修正。
In 3d scanning system based on dot laser, artificial neural networks are used for calibrating the distortion of CCD range sensor.
双级神经网络的前馈解耦控制提出了具有时变,非线性,不确定性和多变量耦合发酵过程中。
A double-level neural network for feedforward decoupling control is proposed for the fermentation process characterized with time-variable, nonlinear, uncertain and multivariable coupling.
双级神经网络的前馈解耦控制提出了具有时变,非线性,不确定性和多变量耦合发酵过程中。
A double-level neural network for feedforward decoupling control is proposed for the fermentation process characterized with time-variable, nonlinear, uncertain and multivariable coupling.
应用推荐