Experiments of Fast Learning with High Order Boltzmann Machines

This work reports the results obtained with the application of High Order Boltzmann Machines without hidden units to construct classifiers for some problems that represent different learning paradigms. The Boltzmann Machine weight updating algorithm remains the same even when some of the units can take values in a discrete set or in a continuous interval. The absence of hidden units and the restriction to classification problems allows for the estimation of the connection statistics, without the computational cost involved in the application of simulated annealing. In this setting, the learning process can be sped up several orders of magnitude with no appreciable loss of quality of the results obtained.     

Implementation of a vector quantization codebook design technique based on a competitive learning artificial neural network

We describe an implementation of a vector quantization codebook design algorithm based on the frequencysensitive competitive learning artificial neural network. The implementation, designed for use on high-performance computers, employs both multitasking and vectorization techniques. A C version of the algorithm tested on a CRAY Y-MP8/864 is discussed. We show how the implementation can be used to perform vector quantization, and demonstrate its use in compressing digital video image data. Two images are used, with various size codebooks, to test the performance of the implementation. The results show that the supercomputer techniques employed have significantly decreased the total execution time without affecting vector quantization performance.This work was supported by a Cray University Research Award and by NASA Lewis research grant number NAG3-1164.     

上海市电话局用户接入网发展状况

上海市电话局用户接入网建设经历了调研、网络规划、启动实施和进一步完善、规范四个怅阶段、现已基本形成了覆盖政府机关、大专院校、医院、商务大楼及高层建筑、新建住宅小区、区级以上图书馆等范围的用户光纤网络，为加快经济建设步伐、满足多层次用户需求、拓展电信新业务打下了坚实基础。     

Integrating neural network technology and noise analysis

The integrated use of neural network and noise analysis technologies offers advantages not available by the use of either technology alone. The application of neural network technology to noise analysis offers an opportunity to expand the scope of problems where noise analysis is useful and unique ways in which the integration of these technologies can be used productively. The two-sensor technique, in which the responses of two sensors to an unknown driving source are related, is used to demonstration such integration. The relationship between power spectral densities (PSDs) of accelerometer signals is derived theoretically using noise analysis to demonstrate its uniqueness. This relationship is modeled from experimental data using a neural network when the system is working properly, and the actual PSD of one sensor is compared with the PSD of that sensor predicted by the neural network using the PSD of the other sensor as an input. A significant deviation between the actual and predicted PSDs indicate that system is changing (i.e., failing). Experiments carried out on check valves and bearings illustrate the usefulness of the methodology developed.     

Determination of assimilable organic carbon (aoc) in ozonated water with acinetobacter calcoaceticus

The effect of ozone application in drinking water on the production of assimilable organic carbon (AOC) was evaluated. The typical procedure to determine AOC is suggested by van der Kooij, which is the method of bacterial growth measurement by colony‐forming units using the strain P17 and/or NOX. The bacterial indicator species used for this study is Acinetobacter calcoaceticus which was isolated and identified while ozonating Nakdong river water. This strain could never be isolated from the raw water, but this strain was the predominant isolate in the ozonated water. Within a short incubation time, this organism was found to replicate well on acetate and oxalate as the sole carbon sources. The yield coefficients of this organism for acetate and oxalate are the same order of magnitude as the value of P17 and NOX. With full‐scale experiments, A. calcoaceticus concentration was found to increase after ozonation, but did not decrease upon chlorination. In laboratory‐scale experiments with Yongsan river water, aldehyes were found to be produced in proportion to the ozone dose. The raw water contains low concentrations of aldehydes, but has a high AOC concentration. A correlation between aldehyde production and AOC production was observed in the tested water with ozonation.     

一种多输入队ATM交换结构

本文提出一种多输入排队ＡＴＭ交换结构和相应的输出冲突解决方法，它可以使交换网络避免输入队固有的排头阻塞，从而使网络在不增加运行速率的情况下，可达到输出排队的性能。文中介绍了冲突解决办法及其实现技术，说明它可方便地在高速网中实现。     

Netware的数据封锁机制与应用程序设计

文章较详细地讨论了Ｎｅｔｗａｒｅ的数据封锁机制，并介绍了Ｎｅｔｗａｒｅ应用程序的设计方法。     

解线性及二次型规划问题增广的神经网络

本文提出了一个解线性及二次型规划问题的神经网络模型，证明了该网络是全局稳定于平衡点，而平衡点就是线性及二次型规划问题的解，该网络的优点是能够实时获得问题的精确解，且可以同时获得带等式不式约束的对偶问题解，该网络易于电路实现。     

中国爆破安全网

中国爆破安全网是由中国工程爆破协会主办的涉爆行业信息专业网 ,开通于 2 0 0 3年 4月。该网是民爆器材生产流通主管部门、使用部门和公安机关实施联网监控和规范化管理的有力工具 ,最主要的功能是为涉爆行业管理部门和从业单位提供一个功能完善的管理和办公平台。该网的开通 ,有利于民爆器材生产、销售、购买、使用流向监控制度的贯彻实行。文章介绍了网络的组成、建设原则 ,并给出了中国爆破安全网网络拓扑图     

无约束淬火机目标温度神经网络预报

淬火、控制冷却的冷却速度和目标温度是关系到钢板性能的关键因素 ,但由于冷却过程的水量、水温、辊道速度等对冷却目标温度的影响属多变量非线性过程 ,用简单的解析模型通常精度较低 ,难以达到精确控制的要求。采用人工神经网络技术对无约束淬火机目标温度进行快速预报 ,结果表明 ,预测精度高 ,快速准确