Neural networks,rational functions,and realization theory

The problem of parametrizing single hidden layer scalar neural networks with continuous activation functions is investigated. A connection is drawn between realization theory for linear dynamical systems, rational functions, and neural networks that appears to be new. A result of this connection is a general parametrization of such neural networks in terms of strictly proper rational functions. Some existence and uniqueness results are derived. Jordan decompositions are developed, which show how the general form can be expressed in terms of a sum of canonical second order sections. The parametrization may be useful for studying learning algorithms.This work was supported by the Australian Research Council, the Australian Telecommunications and Electronics Research Board, and the Boeing Commencai Aircraft Company (thanks to John Moore).     

基于CF的全集成MOSFET—C六阶低通滤波器的仿真分析

本文提出了以电流跟随器ＣＦ为基本电路元件的全集成ＭＯＳＦＥＴ－Ｃ精确连续时间六阶低通滤波器电路，并应用ＰＳＰＩＣＥ－Ⅱ通用模拟电路程序，对其幅频特性和相频特性进行了计算机仿真分析，得出了实用的结论。     

快速二阶BP网络及其在城市用水量预测中的应用

针对BP网络收敛速度慢，易导致局部极小值的缺点，提出一种快速二阶BP网络，并以城市年用水量预测为例，与BP网络对比，结果表明，该方法加快了收敛速度，提出了结果的准确度。     

一种MPEG2视频编码的神经网络自适应量化算法

本文在ＭＰＥＧ２ＴＭ５建议我自适应量化策略的基础上，提出了一种ＭＰＥＧ２视频编码的神经网络自适应量化算法。     

应用ART2人工神经网络自组织形成焊缝图象中的典型空间模式

应用ＡＲＴ２人工神经网络算法，使采集到的焊缝横截面方向上的灰度分布数据自组织形成若干种空间模式，并把它们作为典型空间模式存储在ＡＲＴ２人工神经网络的ＬＴＭ中。对实时采样到的灰度分布进行空间模式匹配程度检验，根据模式分布情况确定出焊缝位置。文中对梯度法检测结果进行了分析和比较，结果表明基于ＡＲＴ２人工神经网络的焊缝位置检测方法具有更强的噪声抑制能力，因而检测结果更准确、可靠。     

Sidle的远程执行设备

Ｓｉｄｌｅ系统是运行在ＳＵＮ工作站网络上的一组实用程序，利用空闲的处理机资源进行大粒度的并行计算．同其它远程执行设备相比，它能支持程序内部并行和嵌套的远程执行，允许一个服务员机接受多个远程执行任务．本文介绍了这些特点和透明性的实现方法．     

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.     

Reliability and performance analysis of time – space – time switching networks with multiple separated space switches

Since electronic switching systems usually require very strict reliability requirements as well as good performance objectives, we need to jointly analyse the performance and reliability of switching systems. In this paper, we compare conventional time–space–time switches with single space switches with those with multiple separated space switches, from the viewpoints of reliability and performance. We consider time–space–time switching networks which consist of N incoming time switches, i.e. one NxN space switch, two (N/2)x(N/2) space switches, and four (N/4)x(N/4) space switches. We introduce a Markov reliability model to study the effect of failures and analyse the reliability and performance of three different types of switching networks in terms of average blocking probability and the mean time to unreliable operation, as we vary the offered traffic. As a result, T–S–T switching networks with multiple separated space switches exhibit better performance and reliability than those with single space switches.     

综合应用地震属性、测井数据反演储层参数

本文研究了样点地震属性的特征提取，利用BP神经网络建立测井声波时差和地震属性的非线性映射关系。采用距离加权平均对研究区所有井的反演结果进行外推。为了提高分辨率和计算结果的准确性，详细分析、研究了适合于地震信号分解和重构的小波，以及测井声波时差和地震波阻抗与层界面的关系。最后，对反演的声波时差资料进行界面影响校正，进而计算出较符合实际情况的孔隙率参数。经已知井和新钻井验证，计算结果和实际情况相一致，效果令人满意。     

Distributed memory systems for simulating artificial neural networks

In executing tasks involving intelligent information processing, the human brain performs better than the digital computer. The human brain derives its power from a large number [O(10¹¹)] of neurons which are interconnected by a dense interconnection network [O(10⁵) connections per neuron]. Artificial neural network (ANN) paradigms adopt the structure of the brain to try to emulate the intelligent information processing methods of the brain. ANN techniques are being employed to solve problems in areas such as pattern recognition, and robotic processing. Simulation of ANNs involves implementation of large number of neurons and a massive interconnection network. In this paper, we discuss various simulation models of ANNs and their implementation on distributed memory systems. Our investigations reveal that communication-efficient networks of distributed memory systems perform better than other topologies in implementing ANNs.