查询词典 neural

Therefore, to counter the possible problems to be met in the application, we study objectively the model structures, algorithms and capabilities for these neural networks, such as the quick learning of the multilayer feedforward network, the learning algorithm of increasing the storage capacity and the convergence radius of Hopfield network, the structure and mapping capability of the fuzzy inference network, the automatic learning of the fault diagnostic expert network and so on.

分别研究了多层前馈网络的快速训练问题、增大Hopfield网络存贮容量和收敛半径的学习算法、模糊推理网络的模型和映射能力，以及故障诊断专家网络知识的自学习问题等。

The new transient chaotic neural network algorithm selectively carefully searchs some states to clarify distribution of small and convergence region during chaotic search.

然后根据这些先验信息，更合理地控制暂态神经元的动力学行为。

By analysis of such models, a method, which is used to find out the region of convergence and to study the local stability for strong nonlinear system, are derived. Thus, we can consider the strong nonlinear neural networks using such method.

利用新的比较方法，考虑了具变时滞和常恢复率的同质人群HIV梯度传染病模型，得到了一个阈值，当阈值小于1时，疾病消除平衡点全局指数渐近稳定，当阈值大于1时，传染病平衡点存在唯一，同时得到该传染病平衡点局部指数渐近稳定的充分条件。

The convergence theorem of the neural networks algorithm and the theorem of numerical integration solution and its inferences are presented and proved.

摘要该文提出了一种基于三角基函数神经网络算法求解数值积分的新方法，提出并证明了神经网络算法的收敛定理和数值积分的求解定理及推论。

A neural network model with the global convergence is proposed and studied in this paper.

本文提出并研究了一种具有全局收敛特性的神经网络模型。

It means that the works of this thesis effectively increase the convergency and accuracy of neural network.

这充分表明了本论文提出的各种改进方法的有效性。

The convergency speed of the modified BP neural network is increased by one or two orders of magnitude.

改进后的BP神经网络的收敛速度提高了1～2个数量级。

For solving problem (1), this dissertation first presents a sufficient and necessary condition by dealing with inequalities using projection operator in convex analysis, and then proposes a kind of new neural network model based on the constraint domain:〓(2) Where P is a projection operator on Q.

本文利用凸分析中的投影算子处理不等式约束，首先给出二次规划问题(1)解存在的充分和必要条件，据于此提出一种新的基于约束区域神经网络模型〓(2)来进行求解，其中P为Q上的投影算子。

Chapter 3 is focused on the neural network optimization model of arbitrary convex function with linear constraints.

早期应用于军事领域的两大技术—扩频技术和阵列信号处理技术已经或即将应用于民用的移动通信系统。

This paper presents a new optimized neural network for nonlinear convex programming problems with both quality and inequality constraints.

目的 为解决一类同时含有等式约束和不等式约束的混杂约束的非线性规划问题。

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。