Car used to enhance learning (Q learning), using neural network Q function approximation.
小车采用加强学习(Qlearning)，采用神经网络对Q函数逼近。
It is to select product samples, then to use methods of function approximation and set up model.
首先选取产品样本，然后采用函数逼近方法建立评价模型。
Presently it has been widely used in pattern recognition, function approximation and data mine etc.
目前，已被广泛应用于模式识别、函数逼近、数据挖掘等领域。
The related continuity, function approximation ability and computational capability theorems are proved…
证明了相应的连续性定理 ，逼近定理 ，计算能力定理等。
The network has the advantages of less hidden layers, simple operation and powerful function approximation capacity.
该网络具有隐层少，运算简单和函数逼近能力强的特点。
This paper deals with the computational model for fuzzy reasoning neural network and its function approximation capability.
研究了模糊推理神经网络计算模型及其连续函数逼近能力。
So there has been a great deal of interest in applying model-free methods such as fuzzy systems for nonlinear function approximation.
因此依然有很多场合需要使用无模型方法—如用模糊系统进行非线性函数逼近等。
Then the Neural Network PID control is realised in the model. This method makes full use of nonlinear function approximation of the Neural Network.
这种方法充分利用了神经网络的非线性函数逼近能力，构造神经网络自整定PID控制器。
In the present paper the convergence and validity of the results of boundary collocation procedure are studied by considering function approximation.
本文从函数逼近的观点研究了边界配置法解的有效性及收敛性。
Secondly, in conditions of non-steady flow, azinuthal velocity and shear stress distribution were deduced according to function approximation method.
在非稳流下，采用函数拟合法，得出流体切向速度随半径变化的表达式及流体所受切向剪切力和分布曲线。
Function approximation is one of the most important ability of ANN, a function object can be replaced by an ANN model with function approximation ability.
函数逼近能力是ANN具有的重要性能之一，依据ANN具有的函数逼近能力，可用ANN模型去替代一个确定的物理对象。
An appropriate selection of basis function directly in?uences the learning performance of a policy iteration method during the value function approximation.
该算法先用渐进方法进行多序列比对，然后通过迭代策略，利用上一轮多序列比对结果修正指导树，产生新一轮比对。
An appropriate selection of basis function directly in? Uences the learning performance of a policy iteration method during the value function approximation.
在策略迭代结强化学习方法的值函数逼近过程中，基函数的合理选择直接影响方法的性能。
As one of the most important capability of ANN, function approximation ability can be used to design ANN model, which can characterize certain physics object.
函数逼近能力是ANN具有的重要性能之一，依据ANN具有的函数逼近能力，可用ANN模型去替代一个确定的物理对象。
Based on the learning characteristic of neural network and the function approximation ability of the wavelet, a new self tuning control algorithm is presented.
依据小波的非线性逼近能力和神经网络的自学习特性，提出了一种基于小波神经网络模型的自校正控制算法。
A new recurrent neural network based on B-spline function approximation is presented. The network can be easily trained and its training converges more quickly.
提出一种新的基于基本样条逼近的循环神经网络，该网络易于训练且收敛速度快。
SVM is a kind of general learning algorithms, which has been widely used in pattern recognition, regression estimation, function approximation, density estimation, etc.
支撑矢量机是一种普适的算法，已经广泛地用于模式识别、回归估计、函数逼近、密度估计等方面。
The theoretical basis of ANN is function approximation, it USES a two - level feedforward neural network to approach arbitrary function to realize better power flow control.
径向基函数神经网络的理论基础是函数逼近，用一个两层的前向网络去逼近任意函数，以更好地进行潮流控制。
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.
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。
This theorem simplifies greatly the analysis of the function approximation ability of FFMLNN because one needs only to study the one dimensional function approximation ability of FFMLNN.
也就是说我们只需研究其一维函数逼近能力，所得的结论完全适合于多维情形，该定理大大简化了前馈多层神经网络函数逼近问题的分析难度。
In this paper, the characteristic and performance of various fast BP algorithms are generalized and contrasted through study on simulation of nonlinear function approximation experiment.
对几种快速BP算法的特点及性能作了归纳和对比，并对一个非线性函数逼近实例进行了仿真研究。
This paper introduces the radial basis function (RBF) network in the seismic data processing, and realizes the inserting data in seismic data processing with function approximation method.
该文将径向基函数网络引入地震数据处理中，实现了函数逼近法地震数据的插值处理，在实际地震数据处理中取得了较好的应用效果。
For the problem that the input and output of real systems is a continuous process relative to time, this paper proposed a process neural network model for continuous function approximation.
针对实际系统的输入输出是与时间有关的连续过程，提出了一类用于连续过程逼近的过程神经元网络模型。
The RBF network function approximation theory and method are introduced, and the method of nonlinear error correction of sensor is presented based on generalized regression neural network(GRNN).
介绍了径向基函数网络的函数逼近原理和方法，提出了一种基于广义回归神经网络（GRNN）的传感器非线性误差校正方法。
After deficiencies of the FIR based orthogonal filter are analyzed, this paper, based on function approximation, theoretically proves that orthogonal wavelets can best approximate the ideal filters.
针对F I r正交滤波器方法的缺点，本文根据函数逼近理论，在理论上，证明了正交小波函数可以最佳一致逼近理想滤波器。
This article indicates the principle for ANN bus protection based on function approximation ability, analyzes the functional relation of bus-bar object and builds the ANN model of bus-bar protection.
叙述了基于ANN函数逼近能力的母线保护原理，分析了母线保护物理对象的函数关系，构建了母线保护的人工神经网络模型。
The problems of universality and extensibility in nonlinear function approximation using small samples can be solved by the method, it a very efficient technique for nonlinear function approximation.
支持向量机方法能够解决小样本情况下非线性函数拟合的通用性和推广性的问题，是求复杂的非线性拟合函数的一种非常有效的技术。
The algorithm is applied to XOR problem and nonlinear function approximation. Simulation results show that the chaos-BP algorithm needs shorter learning time than that of the standard BP and fast BP.
采用混合算法对XOR问题和非线性函数进行仿真，结果表明该算法明显优于标准BP算法和快速BP算法。
The algorithm is applied to XOR problem and nonlinear function approximation. Simulation results show that the chaos-BP algorithm needs shorter learning time than that of the standard BP and fast BP.
采用混合算法对XOR问题和非线性函数进行仿真，结果表明该算法明显优于标准BP算法和快速BP算法。
应用推荐