神经网络

Approximation and projection theory in non-Euclidean and non-linear space; The framework of learning theory, learning algorithm and design strategies based on global architecture approximation.

也就是从整体结构理论上，把人工神经网络的信息处理看作为神经场的组织变换和反应变换两个过程的复合。

A one-level inverse-pendulum is taken as a object for study to design the structure of fuzzy controller.

如MIMO模糊控制器结构及其控制策略、神经网络结构和控制算法以及MIMO系统神经网络解耦控制等问题。

A kind of calculus method that is used to determine the truth-values of propositional logic formulae by means of the dynamic neural networks is proposed. It is not necessary that the formulae be simplified into normal form.

提出一种利用神经逻辑单元动态地构造神经网络的算法来对一些逻辑系统中的逻辑公式的真值进行计算。

With the structure of FNN turning more complex, the good approach or classification is hard to get because of redundancies and uncertainties caused by both large volume uncertain data and lack of prior knowledge. Based on high order spectral reduction for rulers, a new structure changed Fuzzy Neural Network is proposed.

针对先验知识不完备和不确定的情况下海量数据造成的冗余和互斥，模糊神经网络结构变得复杂化并不能很快逼近和分类输出对象的情况，提出了一种基于高阶谱完成规则约简的变结构模糊神经网络的模型。

Aiming at the characteristics of strong nonlinear, large delay, indeterminacy in pH neutralization in sugar mill, this paper combines fuzzy inference system with neural network and introduces an adaptive neuro-fuzzy inference system and builds the model of pH neutralization process.

针对糖厂pH中和过程具有强非线性，大滞后性，不确定性等特点，将模糊推理系统和神经网络相结合，介召了一种自适应神经模糊推理系统，并建立了pH中和过程的模型。

The link weights are adaptively changed in the evolution of network.

作者利用新近发现的一些神经生物学知识，构造了一种新的联想记忆动态神经网络模型。

This paper discusses the structure and algorithm of dynamic neural network, and use this dynamic network to predict the response of Duffing equation and a real structure in different input conditions.

讨论了动态神经网络结构及其算法，然后利用所设计的动态神经网络对杜芬方程和一实际结构在不同输入条件下的响应进行预测。

Making use the function of the memory and the study based on fuzzy neural network ,adopting genetic algorithm and Back-Propagation algorithm together,impling a type of improvement controlling system.

充分利用神经网络控制理论中的记忆和学习功能，采用动态反向传播算法和遗传算法相结合，实现改进型模糊神经控制器。

The inverse model of the system which can be established by neural network according to the UAV's movement is connected with the object controlled so that the nonlinear and correlative system will become linear and irrelated. PID reactive control is used to improve the performance.

根据无人机发生故障时非线性运动的特点，确定适当的神经网络结构建立无人机非线性系统的逆系统，并与被控对象串连可以对非线性耦合系统进行线性化解耦，然后引入PID反馈控制进一步提高神经网络逆控制系统的性能。

Previous studies have identified that understanding other's mind engages a neural circuit consisting of the medial prefrontal cortex, temporoparietal junction, superior temporal sulcus, temporal pole, and precuneus/posterior cingulated cortex. However, due to the limitation of experimental paradigms and neuroimaging data analysis approach, the exact neurocognitive mechanisms that underlie the understanding of others' belief remain unclear.

尽管前人的研究已发现内侧前额叶、颞顶联合皮层、后扣带回/楔前叶以及颞上沟等脑区参与他人信念理解，但是，由于实验范式本身和脑成像数据分析方法的局限性，过去的研究工作没有提出准确的认知神经机制来解释相关脑区组成的神经网络如何协同工作、完成视角转换以保证正确理解他人的信念。

We have no common name for a mime of Sophron or Xenarchus and a Socratic Conversation; and we should still be without one even if the imitation in the two instances were in trimeters or elegiacs or some other kind of verse--though it is the way with people to tack on 'poet' to the name of a metre, and talk of elegiac-poets and epic-poets, thinking that they call them poets not by reason of the imitative nature of their work, but indiscriminately by reason of the metre they write in.

索夫农 、森那库斯和苏格拉底式的对话采用的模仿没有一个公共的名称；三音步诗、挽歌体或其他类型的诗的模仿也没有——人们把&诗人&这一名词和格律名称结合到一起，称之为挽歌体诗人或者史诗诗人，他们被称为诗人，似乎只是因为遵守格律写作，而非他们作品的模仿本质。

The relationship between communicative competence and grammar teaching should be that of the ends and the means.

交际能力和语法的关系应该是目标与途径的关系。