例如，某些基本的神经网络，它们的感知器只倾向于学习线形函数(通过划一条线可以把函数输入解析到分类系统中)。
For instance, a certain kind of basic neural network, the perceptron, is biased to learning only linear functions (functions with inputs that can be separated into classifications by drawing a line).
神经纤维和接收器形成的网络系统接收诸如触摸、温度、疼痛这样的感觉，传递给大脑。
A network of nerve fibers and receptors pick up feelings such as touch, temperature, and pain, relaying them to the brain.
一个使用这个规则的神经网络称为感知器，并且这个规则被称为感知器学习规则。
A neural net that USES this rule is known as a perceptron, and this rule is called the perceptron learning rule.
神经网络：无论什么传感器都会被作为探测输入，输出则是同步按键，这是一个直接并且简单的模型。
Neural-Networks: This would have been a very simple and straightforward model where the inputs are whatever sensors we give the probes, and the outputs are key-presses.
Bayesian网络或神经网络等技术使用表达能力非常强的模型，力求生成无偏向的分类器来“描述”文档集。
Techniques such as Bayesian networks or neural networks use highly expressive models, which try to produce a non-biased classifier in order to "describe" a corpus of documents.
使用高分辨率的MRI扫描器，Thompson教授得以识别出人脑中的内部神经网络，并标记它们的速度。
Using high resolution MRI scans, Dr. Thompson was able to identify the internal network inside people's brains, and map their speed.
本文分析了原有的DGA故障诊断方法，包括三比值法、人工神经网络法、模糊理论、变压器诊断专家系统、灰色关联算法等。
The article analyses original methods of DGA fault diagnose, include three-ratio method, artificial neural network method, Fuzzy Theory, diagnosing expert system, grey relational algorithm, et.
作为神经网络控制的基本单元，采用不同学习规则的神经元控制器，对神经元的学习过程将产生不同的影响。
As the basic unit of Neural Network, Neural Controllers with different learning rules will result in different control effects for the learning process of synaptic weights.
根据电液伺服系统的故障特点，本文提出了采用模糊神经网络做在线辨识器的容错控制方案。
According to fault characteristic of the electro hydraulic servo system, this paper has proposed a fault tolerant project that USES the fuzzy neural network as an identifier on-line.
类神经网络的特色是由一些互相连接的处理器或节点组成。
A neural network typically consists of a number of interconnected processors, or nodes.
特征量被预处理后，输入到集成bP神经网络分类器中分类。
Finally, the features are preprocessed, then classified by integrating BP neural networks.
作者采用人工神经网络来实现光学电流互感器线性双折射效应的补偿。
The authors realize the compensation of optical current transducer's linear birefringent effect by using artificial neural networks.
实验证明基于多传感器和人工神经网络的焊接质量检测系统是有效的。
The experiments show that the welding quality prediction system based on more sensors and ANN is efficacious.
论文将基于神经网络算法补偿传感器测量误差的方法，应用到水利测量技术中。
The method which sensor error is compensated with the artifical neural network algorithms is applied to the hydraulic measurement technique.
用BP人工神经网络分类器进行识别，结果表明矩特征的识别率较高，说明该方法具有良好的应用效果。
The recognition with BP artificial neural net grader shows that the recognition rate of moment features is rather high, this indicates that this method has better applicable effect.
动态图形模拟器是从属于集成环境，并受之驱动的专用模拟器，它实现了神经网络动态变化过程的模拟。
The dynamic graphical simulator which realizes the dynamic procedure simulation of artificial neural network is driven by and belongs to this environment.
结果表明，相对于常规PD控制器，该神经网络控制器具有自学习、自适应功能，位置跟踪获得了满意的控制效果。
The simulation results prove that the neural network controller has self-learning and self-adaptive ability by comparison with PD controller. The position tracking control obtains satisfactory effect.
利用神经网络拟合发动机飞行条件、状态与控制器参数之间的关系，验证了控制器在全飞行包线内的性能。
Using neutral networks, the relationship between engine flight conditions, states and the parameters of controller are fitted, and the controller characteristics in full flight envelope are verified.
本文使用有序神经网络和改进的模糊控制器构成了一种新型的神经模糊预测控制方法。
A new method of neural fuzzy predictive control using ordered neural networks and a improved fuzzy controller is presented.
其主要特点是能够提供一个跟踪网络来辩识系统模型，进而确定控制器的网络参数，实现间接自适应神经网络控制。
Its major feature is that it can provide a tracing network to identify system model so as to determine the network parameters of the controller and realize an indirect adaptive neural network control.
盒维数的简单统计结果可以作为PQ神经网络分类器的输入特征量。
After simple statistics, the dimension can act as the input vector of ANN for PQ classification.
本文根据变量泵的具体情况，为其设计了自适应的神经网络模糊控制器，实现了变量泵的智能控制。
This paper describes that the combination of neural networks and fuzzy controller make the designing an intelligent controller for variable piston pumps become feasible and realistic.
仿真结果表明，所设计的模糊神经网络控制器能有效地减少单交叉口平均车辆延误，具有较强的学习和泛化能力。
Results of simulation show that the fuzzy neural controller can not only decrease the average vehicle delay but also possesses excellent abilities of learning and generalization.
然后，基于某型小卫星的姿态控制问题，设计了高精度定向阶段的神经网络补偿控制器。
Then, base on the problem of attitude control of a satellite under development, we design a NN compensation controller for high accuracy orientation phase.
采用基于灵敏度分析的BP神经网络模型作为基分类器，进一步剔除冗余基因。
BP neural network based on sensitivity analysis is used as base classifier to learn the subsets and redundant genes are further removed.
采用模糊神经网络结合常规PD控制器的方法来进行机器人的运动控制，提出了提取模糊规则的方法。
Fuzzy Neural Network combined with conventional PD controller is used for the kinematics control and a fuzzy rule extraction method is put forward.
还利用三种飞机缩比模型的暗室测量数据，研究了时延神经网络分类器中时延单元数目对分类精度的影响以及分类器的分类性能。
The effect of time delay unit number on classification precision and the performance of TDNN classifier using three typical aircraft dark room data measured with scale model were studied.
软件以环氧乙烷反应器神经网络模型为核心，包括训练、回忆、预测及说明四个部分。
The ANN model of oxirane reactor is the core of the software, and training, recalling, predication and illustration are included.
软件以环氧乙烷反应器神经网络模型为核心，包括训练、回忆、预测及说明四个部分。
The ANN model of oxirane reactor is the core of the software, and training, recalling, predication and illustration are included.
应用推荐