The learning algorithm is BP (Back Propagation) algorithm.
学习算法为反向传播算法。
Several computer simulations show advantages of the learning algorithm.
计算机实验结果说明了学习算法的优越性。
The selection for input variables and the learning algorithm are analyzed in detail.
详细地对输入量的选择和学习算法进行了分析。
Simulation shows that the learning algorithm has a fast convergence speed and good stability.
仿真表明，该学习算法收敛速度快、稳定性好。
In other words, we let the learning algorithm tell us which instances to label, rather than selecting them randomly.
换句话说，让我们学习算法告诉我们，到标签的实例，随机选择，而不是他们。
The efficiency of artificial neuron is promoted and a new model of artificial is created by studying the learning algorithm.
通过研究神经元学习算法，提高神经元的学习效率，并且提出一种新的神经元模型。
So the learning algorithm is convergent and the network , which can approximate to arbitrary continuous function , is stable.
该网络能逼近任意的连续函数，且具有较好的稳定性。
Next, it is discussed how to acquire pointing out information and how to incorporate pointing out informations into the learning algorithm.
其次也讨论了如何获取提示信息和如何将提示信息并入学习算法。
The discounted least squares (DLS) principle is borrowed to construct the learning algorithm of DLS-RBF based upon squared error criterion.
借用打折最小平方(dls)原理构建了基于误差平方准则的DLS R BF网络的学习算法。
The less informative features not only make the learning algorithm weaker, but also conceal the intrinsic characteristic behind the dataset.
那些信息量小的特征的存在，不仅使得学习算法表现不佳，而且会掩盖数据背后重要的本质信息。
Every action has some impact in the environment, and the environment provides feedback in the form of rewards that guides the learning algorithm.
每种行为都对环境有影响，环境提供用于改进学习算法的反馈。
Notice something important here: in the classification problem, the goal of the learning algorithm is to minimize the error with respect to the given inputs.
请注意这里提到的一个问题：在分类问题中，学习算法的目标是把给定输入中的错误最小化。
This thesis researched the models and the learning algorithm of neural network, raised a main steam control system of power station based on neural network.
本文有针对性地对人工神经网络的各种网络模型及学习算法进行了研究，提出一了种基于人工神经网络的电厂主汽温控制系统。
The learning algorithm of membership function based on the RBF Neural Network is discussed and an example is given to demonstrate the validity of this algorithm.
文中探讨了一种用于提取模糊规则的RBF神经网络结构，提出了基于此网路结构的模糊隶属度函数学习算法，最后给出了用于验证该算法有效性的仿真实例。
The learning algorithm is given, and the effectiveness of the model and algorithm is proved by tertiary oil recovery process simulation of oil reservoir development.
文中给出了学习算法，并以油藏开发三次采油过程模拟为例验证了模型和算法的有效性。
The paper presents a new adaptive control system based on PID-like neural network, gives the learning algorithm of this new controller and analyses stability of the control system.
本文提出了一种新的基于PID型神经网络的自适应控制系统，给出了神经网络控制器的学习算法和控制系统的稳定性分析。
The BFNN's hidden layer neurons are divided into several groups, and each hidden layer connects with only one output neurons. The Learning algorithm used by BFNN is similar to BP's.
BFNN的隐层神经元与输出神经元之间为分组对应关系，采用的学习算法与标准BP算法类似。
Furthermore, the experiment using the learning algorithm to model a servo-mechanism and to construct the fault diagnosis system based on the model is carried out, the results is very good.
用这种学习算法建立某伺服机构的模型，并构造基于模型的故障诊断系统，通过实验取得了较好的结果。
The learning algorithm and the characteristics of the fuzzy rules model which can approximate the experiment data are shown to converge to any arbitrary accuracy by the theoretical analysis.
理论分析说明这种模糊规则后件参数学习算法是收敛的、所建模糊模型能够以要求的精度逼近已知的实验数据。
FCMAC based controller structure and a simple learning algorithm were also proposed. In the learning algorithm only small parts of parameters of the FCMAC were adjusted at each learning iteration.
给出一种基于FCMAC的自学习控制器的结构及合适的学习算法，这种网络每次学习少量参数，算法简单。
A corollary of this principle is that a learning algorithm should never be evaluated for its results in the training set because this shows no evidence of an ability to generalize to unseen instances.
这个原理的一个推论是，一种学习算法永远不会对它训练集的结果进行评估，因为对于一种未知的事例而言，没有证据表明算法具有概括它们的能力。
Since user engagement is a variable that we cannot predetermine, we instead use active learning techniques to apply those interactions (where they exist) to the improvement of the algorithm.
因为用户的参与度是不可预计的，所以我们使用了另外一种方式，我们使用主动学习技术，通过分析用户的交互信息来对算法进行提升。
Classification learning is often necessary when the decisions made by the algorithm will be required as input somewhere else.
如果通过算法作出的决定需要输入别的地方，这时分类学习是必要的。
It is interesting to note that Neural Networks is an evolution of learning-oriented estimation, in which the method algorithm is trained to behave like a human expert.
有意思的是，神经网络是一种对学习型评估的进化，算法经过训练后其行为就像是一个人类专家。
Then some parameters of the controller are modulated by hybrid learning algorithm of ladder descent (LD) and least square error (LSE) so as to attain better control precision.
然后通过梯度下降法和最小二乘法相结合的混合学习算法，对控制器参数进行调整以提高其控制精度。
The results of image edge detection show that the algorithm has better convergence properties than the conventional backpropagation learning technique.
经图像边缘检测应用结果表明，该算法对于加快网络学习的收敛性有着显著成效。
This system, possesses the structure of neural net and learning algorithm, addressed as fuzzy neural net FNN.
该系统具有神经网络的结构和学习算法，称模糊神经网络FNN。
The topologic structure and learning algorithm of the rough neural network are given, and the approximation theorem of the rough neural network is presented.
给出了粗糙神经网络的拓朴结构和学习算法以及粗糙神经网络的逼近定理。
The simulation and motor control show that the new algorithm has fast learning rate, good convergence properties and can overcome the defects of traditional PID algorithm.
仿真实验及在伺服电机转速控制中的应用表明，该算法具有较快的学习速度及良好的收敛性能，并有效地克服了传统PID算法的缺陷。
The scene is different, the detection accuracy is different, the user can put the safety cost is different, the machine learning algorithm is not the same.
场景不同，需要的检测精度不同，企业用户可以投入的安全成本不同，选用的机器学习算法也不相同。
应用推荐