其中，对于多层感知器网络、径向基函数网络、多项式网络尤其关注。
Of great interest, popular multilayer perceptron (MLP), radial basis function (RBF) and polynomial neural networks are the focus of the paper.
最后，本算法与BP神经网络和多项式拟合算法比较，色彩转换精度有明显提高。
Finally, the experiment results compared with the BP neural network algorithm and polynomial matching algorithm show that the new model improves color conversion accuracy effectively.
它可以对多项式函数，神经网络，径向基函数进行训练。
It can train polynomial function, neural networks, or radial basis function (RBF) classifiers.
结合GPS测量和水准测量资料，利用支持向量机方法对GPS高程进行了转换，并与神经网络和多项式拟合等拟合的结果进行了比较，得出了一些有益的结论。
In this paper, a method for converting GPS height to normal one by means of support vector machine is proposed, and compared with the methods of neural network, polynomial fitting etc.
本文研究了这样的特殊情形：树网络上所有起点处于同一条路上，建立了多项式时间算法。
In this paper we study such a special case: a tree network with all sources on a path and we present its polynomial-time algorithms.
以最佳多项式逼近为度量，用构造性方法估计单隐层神经网络逼近连续函数的速度。
With the best polynomial approximation as a metric, the rate of approximation of the neural networks with single hidden layer to a continuous function is estimated by using a constructive approach.
然后由债务信度网络构造了容量费用网络，利用最小费用循环流问题给出了该模型的一个多项式算法。
Then we construct a capacity cost network from the debt credit degree network. Finally, by applying minimum cost circulation flow problem, we give a polynomial algorithm for this model.
本文给出一类适合于求解多项式实零点问题的神经网络。理论分析和模拟结果都表明，这类网络可实时求解多项式实零点问题。
A neural network model for computing real zeros of polynomials is presented. Both the mathematical analysis and the experimental results show that the proposed network is effective.
提出了一种多项式泛函网络运算新模型，来求解任意数域或环上多项式运算问题。
The new computing model of polynomial functional network is firstly proposed and the solving polynomials computing problem in arbitrary coefficients fields or ring is discussed.
无线传感器网络在应用二元多项式密钥预分配协议时，通常容易遭受到敌方的合谋攻击。
Wireless Sensor Network (WSN) was usually vulnerable to conspiracy attack from its adversaries when using bivariate polynomial key pre-distribution protocol.
利用网络编码，允许中间节点进行信息编码，最小能量广播问题可以转化为一个线性规划问题，并且具有一个多项式时间解。
We use network coding, i. e. , allowing intermediate nodes to code, the problem can be formulated as a linear program problem and has a polynomial-time solution.
提出一种新的神经网络枛类模糊神经网络，并以基于多项式系的类模糊神经网络为例作了讨论。
A new neural networkquasi-fuzzy neural network is proposed and discussion is carried out with the quasi-fuzzy neural network based on polynomial series as an example.
给出了具有频道负荷约束的专用移动无线电网络问题的整数线性规划，设计了求解特殊网络的具有频道负荷约束的频道分配问题的多项式时间算法。
An integer programming formulation for channel assignment problem with channel loading is presented and polynomial time algorithms are designed for some special radio networks in this paper.
该文研究了G神经网络的函数映射能力，给出了前馈g神经网络映射任意G型多项式的构造性证明。
In this paper, the function approximation of Gelenbe Neural Network (GNN) is discussed and it is proved that GNN can approximate any G-type polynomial by using constructional method.
详细介绍了用解析解法和数值解法(即矩阵方程的多项式解法)分别求出了基元回路为正方形的“田”字形超导网络在外磁场中的临界温度，结果表明两种计算方法是完全等价的。
The critical temperature of superconducting network which is composed of square unit loops in external magnetic field is solved by means of analytic method and numeric method I.
文章根据组合预测的理论和BP神经网络对非线性数据良好的逼近特性，提出了基于BP神经网络的灰色预测、多项式回归模型的民用汽车运力组合预测模型。
Based upon the theory of combined forecasting, up-standing identity of BP neural network on approaching non-linear data, put forward a combined forecasting model for civil motors.
通过与线性插值、多项式拟合法和神经网络逼近法的比较，可以明显看出用该神经网络算法的优越性。
Compared with linear inserting value and multinomial imitation method, it is obvious that NN has more advantages.
针对点云数据的三维重建问题，提出了一种隐曲面重构的广义多项式神经网络新方法。
A new type of generalized polynomials neural network was proposed to reconstruct 3d implicit surface from the scattered points.
该方法用幂级数多项式拟合传感器的非线性模型，多项式的系数可由神经网络学习算法得到。
The response of the sensor is expressed in terms of its output by a power series. The coefficients of the power series can be learned and determined by a simple neural algorithm.
该方法用幂级数多项式拟合传感器的非线性模型，多项式的系数可由神经网络学习算法得到。
The response of the sensor is expressed in terms of its output by a power series. The coefficients of the power series can be learned and determined by a simple neural algorithm.
应用推荐