神经网络

In three-valued neural networks model, the energy function of two-valued neural networks model can not be applied, so the energy function need to be find for the three -valued neural networks model, and here two kind model algorithms are compared in this paper.

在三值神经网络模型中，二值模型的能量函数不能适用于三值模型，因此需要求解三值模型的能量函数，在此本文对三值神经网络测试生成算法与二值神经网络测试生成算法进行比较。

A neural-network-based robust compensating control method is proposed for the robots with constructed and unconstructed uncertainty The robust controller consists of a computed torque controller and add-on compensating controller The effective way using neural network to estimate the system uncertainty is also given.

四、对具有结构型和非结构型不确定性的机器人提出了一种基于神经网络补偿的鲁棒控制方法，控制器由一个计算力矩控制器和一个可切入的神经网络补偿控制器组成，给出一种利用神经网络学习机器人不确定性的有效途径。

BP neural network based on adaptive UKF is introduced in this paper for the standard BP neural network has slow converges,local minimum value and weak generalization ability.It can train weight of BP and improve the efficiency of BP without linearization by using the frame of Kalman filters and adaptive factor to adjust the variance of dynamic model.

1引言1986年，Rum elhart和M cC lelland等人在多层前向神经网络模型的基础上，提出了误差反向传播学习算法(BackPropagation简写BP)，该算法是目前在神经网络中应用最广泛的算法，它解决了多层前向神经网络的学习问题[1]。

The practicality of using rough set to reduce the date was discussed, in this paper, and the interval-valued continuous attribute discretization by applying self-organizing map neural network clustering was proposed, too. This article proposes a simplified indiscernible matrix's method, which reduces the example's condition attribute and eliminates the redundant information of the date. What's more, it provides the methods used to diagnosis compressor's faults based on the intelligence hybrid system by adopting the MATLAB neural network workbox. At last, the functional modules which make up into intelligence hybrid system for fault diagnosis was introduced, including: data acquisition module, date preprocessor module, date reduction module, neural network module, fault diagnosis module and fault expressing module. Here, the article also gives the flow of work of all the above modules.

论文论述了应用粗集对故障数据进行约简的可行性，并应用自组织映射神经网络的聚类功能，来实现连续属性值的离散化方法；给出了简化的分明矩阵法，并用该方法实现了样本条件属性的约简，消除了样本数据中的冗余信息；采用MATLAB神经网络工具箱建立了压缩机的部分故障类型的智能混合诊断系统；最后介绍了智能混合故障诊断系统的功能模块组成，各功能模块分别为：数据采集模块，数据预处理模块，数据约简模块，神经网络模块，故障诊断模块，故障解释模块；并给出了各功能模块的工作流程。

The adaptive algorithm is adopted to design the concept mapping of cerebella model articulation controller neural network. The nonlinear quantization CMAC is presented to improve the speed and accuracy of calculation to meet the complex and dynamic demand under the nonlinear and realtime controlling environment.

采用自适应算法对小脑模型神经网络的概念映射进行设计，提出了非线性量化小脑模型神经网络算法，提高小脑模型神经网络的计算速度和精度以满足复杂动态环境下的非线性实时控制的需要。

Based on the characteristics of CMAC neural network and fuzzy control,the novel controller of fuzzy CMAC neural network that reflects the fuzziness and continuity of human cerebella is discussed.

针对 CMAC神经网络和模糊控制的特性，给出了一种能反映人脑认知的模糊性和连续性的模糊 CMAC神经网络控制器，该控制器采用高斯函数作为模糊隶属函数，利用神经网络实现模糊推理并可对隶属函数进行实时调整，从而使其具有学习和自适应能力。

The model of Protein Secondary Structure based on the multi-modal neural network This paper proposed a multi-modal neural network predictable model that synthesizes by 7 BP neural network group in protein secondary structure prediction, this model use "profile" encoding method and "the distance" between the amino acid for the excitory input information, has carried on the prediction to the protein secondary structure prediction.

3基于多神经网络的蛋白质二级结构预测模型论文提出了一个由 7 个 BP 神经网络组合成的多神经网络的蛋白质二级结构预测模型，该模型采用&profile&编码方式和氨基酸间的&距离&为激励输入信息，对蛋白质二级结构进行了预测。

In order to apply neural network and intelligent control in supermaneuverable flight, the mathematic model of flighter is obtained, and the nonlinear aerodynamic coefficients are identified using computational neural networks, then, a neural network control system for supermaneuver is designed according to the timescale, and a intelligent compensator is givento compensate for the system errors which are caused by the networks training error, no-samples input, disturbance and time-delay, etc, which including the design of knowledge base, blackboard and reasoning engneer, the simulation results of Herbst maneuver demonstrate the designed control system is satisfying.

为了在超机动中应用神经网络和智能控制，本文接着建立了超机动时飞机的数学模型，并利用神经网络对大迎角下非线性非定常气动力进行了辨识建模，然后按时标分离法设计了一个针对超机动飞行的神经网络控制系统。

Aiming at the major influencing factor of the logistics cost of coal enterprise as well as the non-linear characteristic of the coal enterprise logistics cost and the superiority that the neural network has in the solution of complex nonlinear system question, propos to use the BP neural network to do the forecasting of the logistics cost, establishs the forecast model of the logistics cost and do simulation and forecasting by frondose dates, the result indicates the precision of this forecast method is high, the convergent rate is quick, is one feasible forecast method.

重点针对影响煤炭企业物流成本的因素以及煤炭企业物流成本所具有的非线性特点和神经网络在解决复杂非线性系统问题方面所具有的优势，提出了采用BP神经网络来进行物流成本预测的方法。建立了基于BP神经网络的物流成本预测模型并应用具体数据对模型进行了模拟和预测，结果表明该方法预测精度高，是一种实际可行的预测方法。

On the base of the analysis about the cause why this type of systems is hard to be controlled a new FNN, the FNN based on hyper-cylinder clustering, is presented. By comparison with the FNN based on hyper-sphere clustering, for any sample to be clustered, the FNN based on hypercylinder takes not only its input sample but also its output value into consideration. And so it is impossible for any two samples with'close'input samples and'estranged'output values to be clustered in the same cluster.

借助于对非线性系统模型Ⅱ不可逆情形下难以控制原因的分析，提出了基于超柱体聚类的模糊神经网络，与基于超球聚类的模糊神经网络相比，这种模糊神经网络在聚类时不仅考虑样本中的输入向量，也考虑样本的输出值，因此不会将输入向量较接近而输出值差异较大的两个样本聚为一类。

Singer Leona Lewis and former Led Zeppelin guitarist Jimmy Page emerged as the bus transformed into a grass-covered carnival float, and the pair combined for a rendition of "Whole Lotta Love".

歌手leona刘易斯和前率领的飞艇的吉他手吉米页出现巴士转化为基层所涵盖的嘉年华花车，和一双合并为一移交&整个lotta爱&。

This is Kate, and that's Erin.

这是凯特，那个是爱朗。