混合学习

这是因为混合学习是对传统教学改革和对e-learning反思后变革的融合点（赵丽娟，2004）。

This is because blended learning is a connecting point of traditional teaching and e-learning .

然后再对T-S模糊神经网络的学习算法&BP算法进行分析、改进，给出了改进自适应遗传算法和动量-自适应BP算法相结合的混合学习算法。

BP algorithm which was the learning algorithm of T-S fuzzy neural network had been analyzed and improved , the blended learning algorithm which combined the improved adaptive genetic algorithm and momentum-adaptive BP algorithm was given .

基于混合学习策略的多Agent信息过滤系统

Multi-Agent system for information filtering based on hybrid learning approach

B样条基函数模糊神经网络控制系统及其混合学习算法

A Control System with Fuzzy B-spline Neural Networks and Its Hybrid Training Algorithm

嵌入演化策略的BP混合学习算法研究

Research on the learning algorithm of BP neural networks embedded in evolution strategies

前馈神经网络的混沌BP混合学习算法

Chaos BP hybrid learning algorithm for feedforward neural network

一种新型的混沌BP混合学习算法

A new chaos BP hybrid learning algorithm

混合学习模式ANN组合的研究

Research on the Combination of ANN with Hybrid Learning Pattern

基于混合学习算法的RBF神经网络主蒸汽温度控制

Main steam temperature control using RBF neural network based on hybrid learning algorithm

针对BP算法的不足，使用混合学习算法训练网络，优化了网络参数。

Because of defects of BP algorithm , a hybrid learning algorithm is applied to train and optimize the network parameters .

基于em算法且能以概率1全局收敛的混合学习算法

The Hybrid Learning Algorithm Which is Based on em Algorithm and can Globally Converge with Probability 1

集成GASA混合学习策略的BP神经网络在水稻虫害预测中的应用

Application of BP Networks Based on GASA Hybrid Strategy to Rice Pests Prediction

模糊CMAC神经网络控制系统及混合学习算法

A fuzzy CMAC neural network controller and its mixed learning algorithms

FNN上的竞争学习及混合学习方法

Competition competitive learning and mixed learning methods in FNN

分析了遗传算法（GeneticAlgorithm）和BP算法在模糊逻辑系统参数寻优问题上的优缺点，提出一种基于改进的GA+BP模糊逻辑系统混合学习算法。

The advantages and disadvantages of genetic and BP network algorithm on parameter optimization of fuzzy logical systems were analyzed and an improved hybrid learning algorithm based on GA + BP in fuzzy logical systems was proposed .

针对用户个性化服务的要求，给出了一种基于混合学习策略和BP神经网络的多Agent信息过滤系统实现方案。

With the requirement of user 's specific information service , a framework of multi-Agent system for information filtering , based on hybrid learning approach and BP neural network , was proposed in this paper .

文中还提出了递归模糊神经控制器的混合学习算法，即先采用免疫遗传算法的粗学习，再采用BP梯度算法的细学习。

The mixed learning algorithm of the recursive fuzzy-neural controller is also put forward , including the thick learning of the immune genetic algorithm first , and then the thin learning of the BP algorithm .

探讨了Moodle的架构与搭建，以及Moodle平台上混合学习的策略。

The paper discusses the framework and construction of Moodle , and the strategy of cooperative learning on Moodle .

结合朴素贝叶斯和决策树提出一种用于回归分析的混合学习方法&BRT（BayesianRegressionTree）。该方法基于分而治之原则构造决策树，以朴素贝叶斯取代叶节点。

It proposes a hybrid approach for regression analysis & BRT ( Bayesian regression tree ), which builds tree model by the divide-and-conquer method and uses NBR ( naive Bayesian network for regression ) to replace leaf node .

文中提出一种基于模糊自适应学习控制（FALCON）结构下新型的混合学习控制策略。

A new fuzzy adaptive learning control ( FALCON ), structure based mixture learning control is put forward in the paper .

还提出了控制器参数的混合学习算法，即先采用混沌算法离线优化，再采用BP梯度算法在线调整。

A hybrid learning algorithm for the controller 's parameters is moreover being proposed , i. e. in a first step , chaos optimizing algorithm is used for off-line optimization , followed by on-line adjustment with BP gradation algorithm .

这种新混合学习方法首先利用遗传算法得到ANFIS所有参数的一个全局近似最优解，然后再利用BP算法和最小二乘法分别对前提参数和结论参数进行细化调整。

In this method , a global approximately optimal solution of all ANFIS parameters is obtained using genetic algorithm and then premise parameters and consequent parameters are fine tined respectively using BP algorithm and Least Squares Estimate .

选取LQG控制的仿真结果为T-S模糊控制器的学习样本，采用减法聚类法和混合学习算法对T-S模型进行结构与参数辨识，通过改变结构刚度来检验模糊控制器的鲁棒性。

The subtraction clustering method and the hybrid-learning algorithm are adopted to train the structure and parameters of the T-S controller . The training data are the simulation results of a LQG controller .

讨论了这种控制器的混合学习算法，即先采用混沌算法离线优化，再采用BP梯度算法在线调整，并推导了变形Elmam网络的系统辨识算法。

The mixed learning algorithms of the controller is presented as well , which the learning of the chaos optimal algorithm is firstly adopted offline , then the learning of BP algorithm is used online . The algorithm of system identification based on the modified Elman network is ratiocinated .

针对组合预测比单项预测具有更高的预测精度，本文提出了一种基于模糊神经网络的上市公司被ST的非线性组合建模与预测新方法，并给出了相应的混合学习算法。

As combining forecasts are more accurate than individual ones , this paper presents a new method to set up nonlinear composite and forecast the special treatment ( ST ) for listed firm based on fuzzy neural network , and gives the corresponding composite learning algorithm .

通过模糊聚类和混合学习算法，ANFIS可以逼近高阶输入输出非线性系统，将该算法用于两个典型非线性系统建模，均能获得满意结果。

By using fuzzy clustering and hybrid learning procedures , the ANFIS can construct the highly nonlinear input-output mapping . Then , the ANFIS is used to model two nonlinear systems , both yield remarkable results .

首先提出变形的BP算法IBP，然后将它与Solis和Wets的随机优化算法相结合，提出了新型混合学习算法NHLA。

A new hybrid learning algorithm NHLA , which combines the variant IBP of algorithm BP and the random optimization algorithm presented by Dr Solis and Wets , is presented .

针对上述ANFIS方法，进一步提出了一种两步混合学习算法：首先采用最近聚类算法确定网络的结构和初始参数，然后采用梯度下降法对参数做进一步调整。

Associated with the ANFIS is two-phase hybrid learning algorithm , which utilizes a nearest neighbourhood clustering scheme for both structure learning and initial parameters setting and a gradient descent method for fine tuning the parameters of ANFIS .

在该混合学习算法中，网络的学习任务被分解为2个部分：隐藏层的权值先随机给定，然后使用Alopex算法不断地对其进行扰动；

By using the hybrid learning algorithm , learning tasks are divided into two parts : weights in the hidden layers are given randomly and perturbed continuously in some directions by using Alopex ;

将混合学习算法应用到PTA工业过程中4-CBA含量的软测量建模中，取得了令人满意的效果。

The proposed method has been applied to build a soft-sensor for measuring the 4-CBA concentration in the industrial PTA ( Purified Terephthalic Acid ) oxidation process and the result demonstrates that the proposed method is suitable to practical application .