| 1. | Fifthly , it introduces the basic theory of neural network and it puts stress on the bp computing ways
对神经网络进行了详细地阐述，着重介绍了bp算法。 |
| 2. | This paper includes following parts : at first , the basic theory of neural networks and expert system was analyzed
全文包括以下几个部分:首先分析了神经网络和专家系统的基本原理。 |
| 3. | The basic theory of neural network and the back propagation neural network are represented in chapter 4
第四章对神经网络的基本原理进行了描述，重点介绍了反向传播( baekpropagation )神经网络。 |
| 4. | The design theory of neural networks is discussed , including the basis principles of neuron control and the design of back - propagation network . 4
探讨了面向控制的神经元网络设计理论，包括单神经元控制的结构和基本理论及bp神经网络设计； 4 |
| 5. | Then , because the raw - material mill system has the characteristic of many variables and non - linear , the author studies and models the system with the theory of neural network .
第二，针对生料磨系统具有多变量、非线性等特点，运用了bp神经网络理论对系统进行了建模与研究。 |
| 6. | The design theory of neural networks and the estimations of linear systems and nonlinear systems with dead time using neural network are discussed . neuro - pid internal model control , adaptive pip controller based on neural network and adaptive smith predictor using neural network are proposed for time - delay systems . the simulation experiments and the real - time temperature control of electrical furnace are made
文中着重研究了神经元网络设计理论、基于神经网络的线性和非线性时滞对象辨识及时滞系统控制方法，以此为基础提出了时滞系统神经元自适应pid内模控制、时滞系统神经网络自适应pip控制以及神经网络自适应smith控制方法，并进行了控制系统的实例设计与仿真实验。 |
| 7. | In this thesis , we combine the theory of neural network and traditional image processing technique , analyze and research the topic of the location and recognition of vehicle license plate based on structural alternative covering algorithm , and try to locate the car plate even there exist lots of distributive factors in the image and recognize the characters finally
本文基于构造性的覆盖算法，将神经网络技术和传统的图像处理技术相结合，对车辆牌照的定位和识别进行了较为深入的分析和研究，力求在图像中存在较多干扰因素的情况下仍然能够较好的定位车牌并给出最终的识别结果；论文主要工作和创新点如下： 1 |
| 8. | A general introduction to the thesis : a description of tsp and it ' s mathematical model an introduction of the theories of neural network applied to the tsp an applicative analysis of hnn in solving the tsp the improvement of hnn the presentation of the solutions of large scale tsp based on the idea of sorting the innovations of this thesis : the analysis of the theoretical process of hnn in solving the tsp problem , the new improvment of hnn on the basis of early improvement , which makes the number of neural reduce from n2 to ( n - 1 ) 2 , and amplifies the architecture of neural network , also improves the efficiency . this has great significance in realizing hardware of the neural network . the presentation of the idea of sorting based on delamination in solving large scale tsp
本文所做的工作：给出了tsp问题的描述及数学模型介绍了神经网络应用于tsp问题的相关理论知识hopfield算法在求解tsp问题中的应用分析在已有的改进算法基础上，对hopfield算法进一步改进提出了大规模tsp问题的基于分层聚类思想的解决方案本文的创新之处：分析了hopfield神经网络算法解决tsp问题的理论过程，在已有改进算法的基础上，提出了新的改进，使得构造神经网络的神经元数目由n ~ 2个减少到( n - 1 ) ~ 2个，简化了网络结构，提高了算法效率，对于神经网络的硬件实现有重要的意义；提出采用分层聚类的方法来解决大规模tsp问题的方案。 |
