基于神经网络的VQ图象编码

文章给出将神经网络与矢量量化相结合的两种编码方法，介绍了其原理和实现的算法。经计算机模拟表明，在比特率低于０．３ｂｐｐ时仍可得到高质量的编码图象。     

Effectiveness of spatial representation in the formation of network communities: experimental study on community organizer

In this paper, we present and discuss Community Organizer, a system designed to support network communities. The main characteristic of Community Organizer is the use of spatial representations for the relationships among community members including the communications exchanged among these members. These spatial representations reflect the degree of closeness of interests and concerns among the members, and are intended to provide users with clues on how to form network communities. In order to investigate the effectiveness of the proposed spatial representations, we conducted experiments with two different versions of the software. One version offered meaningful spatial representations while the other version did not. The subjects who used the former software version felt a greater sense of ‘community’, enjoyed using the software more, and actively used it longer than the subjects using the latter software version (control condition). These results indicated that the proposed spatial representations are effective in supporting network community formation.     

一种新型基于石英的热光型光开关

一种采用基于石英的平面光波回路技术（PLC）制造的热光型光开关正越来越引起关注，它具有低耦合损耗、高稳定性及适于大规模集成等优点。首先描述了采用热光相移器构成马赫-曾德于涉仪（MZI）结构的热光型光开关，然后讨论2×2MZI热光型开关的工作原理及基本特性，最后介绍了由2×2MZI热光型开关单元构成的大规模光开关阵列以及一种采用悬梁式结构热光相移器的低功率消耗的光开关。     

一种遗传-梯度混合算法

本文提出一种函数全局优化的遗传-梯度混合算法。该算法由选择、交叉和诱导变异算子组成。通过对自适应滤波和前向神经网络权值训练两个典型问题的数字仿真，表明该算法是一种快速有效的全局优化算法。     

帧中继交换技术

本文论述了帧中继交换的概念、标准，结构、特点网络式样及在互连网中的应用。     

A comparison of backpropagation and general regression neural networks in quantative trace metal analysis using anodic stripping voltammetry and cybernetic instrumentation

A comparison is made between backpropagation and general regression neural networks for the prediction of parts per billion lead concentration when used to process data obtained from digested curry powder by the electrochemical analysis method of differential pulse, anodic stripping at a thin film mercury electrode (TFME). Two data sets are used, one requiring the net to classify an unknown analytical data vector into one of a number of previously learnt concentrations, and one requiring the net to predict the probable concentration of an unknown sample by interpolation of the already learnt concentrations. For both of these data sets the general regression neural network is shown to train faster and to provide results superior to those obtained by backpropagation.     

神经网络余／十转换的数学原理

本文提出了孙子定理的微分方程求解法，讨论了系数为求余算子的非线性微分方程的稳定平衡点和最佳解的误差。本文构造的非线性微分方程可以唯一地收敛于孙子定理的解，其误差可任意小。该微分方程可用人工神经网络实时计算，实现余／十转换。计算机模拟结果证实了本文理论的正确性。     

江苏省本地电话网结构与发展

分片汇接的网状网结构是江苏省本地电话网的基本框架,而汇接局和连接汇接局的传输系统则是网路规划与通信建设的重点。     

基于LONWORKS网络技术的温度控制系统的开发

本文通过一个实例介绍了基于ＬＯＮＷＯＲＫＳ网络技术的温度控制系统的为系统主其开发过程。     

On parity problems and the functional-link artificial neural network

This paper contains the proof of a theorem on the capability of functional-link artificial neural networks both to represent and to learn the n-dimensional parity problem. The result is obtained by an embedding of the problem into a space of dimension 2ⁿ — 1. It is shown that the Volterra expansion of the data in n-dimensions provides the necessary transformation. By computing the parity function, it is shown that a suitable set of neural network weights can be deduced. Finally, it is demonstrated that 2ⁿ — 1 is the minimum embedding dimension for the problem.The contribution of A Zuderell of the University of Innsbruck is acknowledged.