Pattern separation in digital learning nets

Pattern separation is a new technique in digital learning networks which can be used to detect state conflicts. This letter describes pattern separation in a simple single-layer network, and an application of the technique in networks with feedback.<>     

Switching nets and electronic logic circuits

It is suggested that methods of improving the reliability of switching nets are not necessarily applicable to electronic logic circuits.     

Natural pattern clustering in digital learning nets

This letter reports the results of experiments in which an unsupervised net is found to perform a natural-clustering operation. An `aging? process is introduced during learning, and the net is randomly connected with outputs feeding back to inputs.     

Microcircuit learning nets: Hamming-distance behaviour

A probabilistic method based on the Hamming distance is presented for calculating the pattern-recognition response of a class of single-layer microcircuit learning nets. The prediction of the behaviour of a 12-element machine is shown to agree with measured responses. The method is also used to explain the characteristics of nets trained on translated versions     

Recent developments of electronic neural nets in North America

We present a survey of recent electronic implementations of neural nets in the US and Canada with an emphasis on integrated circuits. Well over 50 different circuits were built during the last two years, representing a remarkable variety of designs. They range from digital emulators to fully analog CMOS networks operating in the subthreshold region. A majority of these circutis, over 40 designs, use analog computation to some extent. Several neural net chips are now commercially available, and many companies are working on the development of products for an introduction in the near future.Most of the neural net circuits have been built in standard CMOS technology, except for a few designs in CCD technology. EEPROM cells are investigated by several researchers for building compact, analog storage elements for the weights.While a large number of circuits have been built, there are still only few reports of applications of any of these chips to large, real-world problems. In fact, system integration and applications with neural net chips are just beginning to be explored. We describe some experiences gained with applications of analog neural net chips to machine vision from our laboratory.     

Modeling and simulation of an electronic component manufacturingsystem using hybrid Petri nets

Modelling and analysis for the design and operation of manufacturing systems is a vital need. For semiconductor manufacturing systems, which are large scale systems, discrete Petri nets do not constitute an adequate tool for modeling and analysis. In fact, use of discrete Petri nets is confronted with tile state explosion and the high cost of simulation. In this paper, hybrid Petri nets are presented as powerful tools for modeling and simulation of semiconductor manufacturing systems. This model has been used for modeling and simulation of a real life electronic components manufacturing system. It provides an accurate and first simulation of this system     

Microcircuit learning nets: some tests with handwritten numerals

Networks of adaptive-logic circuits which recognise patterns after being `taught? by an operator have been studied. The letter describes the way in which the performance of such networks may be estimated from a knowledge of the statistical characteristics of the patterns. Results obtained with hand-printed numerals are discussed.     

Automatic classification of mass spectra by means of digital learning nets

The method of pattern recognition by means of s.l.a.m. (stored-logic adaptive modules) has been applied to the automatic classification of mass spectra into broad chemical groups, with zero-error results.     

Microcircuit learning nets: improved recognition by means of pattern feedback

Pattern feedback is a new concept in learning networks of adaptive microcircuits. The net is trained to produce a model output pattern. During use, the output patterns are fed back to the input. Recognition of an input pattern takes place if a stable model output pattern is generated.     

面向认知对抗的学习训练与仿真评估系统设计

针对认知电子战装备面临的作战场景复杂多样、真实数据难以获取、实战训练成本高昂等问题,为满足认知电子战系统方案论证、关键技术研究需求,将人工智能技术与系统仿真技术相结合,通过建立认知电子战装备及其典型作战对象的信号级模型,以及模拟电子战装备与作战对象在复杂电磁环境下的信息交互过程,构建面向未来战场认知对抗的学习训练与仿真...     

Local nets and social capital

This paper examines the relationship between local nets and social capital (networks, support and trust) in local communities. The relationship is examined through a review of literature on local nets and social capital and through an introduction to an ongoing study of a local net in Sweden.In the literature of social science it has been a common theme that changes in urban industrial society have undermined social capital in the community. The development of computer-based communication networks has added a new dimension to the argument, posing the question of whether local nets can (re-)create social capital in local communities. There is a division between those commentators who see local nets as a threat to existing forms of community and others who believe they provide new bases for social capital.In order to examine the impact of local nets on social capital a case study is being conducted of a local net project in a relatively marginalised community in Stockholm. The aim of the local net is to increase social capital in the community, especially with reference to disadvantaged groups. An evaluation of the project is taking place using mixed methodologies, including both quantitative and qualitative techniques.The paper describes the first study in the research project: a survey administrated to residents not yet connected to the local net. Initial analysis suggests that there is a relatively low level of social capital in the community. The respondents, however, have high expectations in relation to the potential of the local net for enhancing social capital. There are few differences in expectation between different groups in the population. This suggests that the local net may well be a way of including disadvantaged groups in the local community (as well as in the wider society).Whether the use of local nets can (re-)create social capital in the local community, only later phases in the research will show. The hypothesis of the research, though, is that the use of local nets will lead to an increase in association, support and trust that provide the foundation for collaboration, common identity and social capital in the community.     

Structuring and composability issues in Petri nets modeling

Along Petri nets' history, numerous approaches have been proposed that try to manage model size through the introduction of structuring mechanisms allowing hierarchical representations and model composability. This paper proposes a classification system for Petri nets' structuring mechanisms and discusses each one of them. These include node fusion, node vectors, high-level nets, and object-oriented inspired Petri nets extensions, among others. One running example is used emphasizing the application of the presented mechanisms to specific areas, namely to automation systems modeling, and software engineering, where object-oriented modeling plays a major role.     

Topology design and bandwidth allocation in ATM nets

The design of a P/S network embedded into a backbone facility network is discussed. The problem is formulated as a network optimization problem where a congestion measure based on the average packet delay is minimized, subject to capacity constraints posed by the underlying facility trunks. The variables in this problem are the routing on the express pipes (i.e. the channels that interconnect the P/S modes) and the allocation of bandwidth to such pipes. An efficient algorithm is presented for the solution of the above problem and it is applied to some representative examples. It is shown that for some test cases the congestion measure is substantially reduced with respect to the values obtained when the embedded topology is kept identical to the backbone topology. Dynamic reconfiguration schemes where the embedded topology is periodically adjusted to track the fluctuations in traffic requirements are discussed     

Task support, reference, instruction, of collaboration? Factors in determining electronic learning and support options

This publication contains reprint articles for which IEEE does not hold copyright. You may purchase this article from the Ask*IEEE Document Delivery Service at http://www.ieee.org/services/askieee/     

Petri nets: Properties, analysis and applications

Starts with a brief review of the history and the application areas considered in the literature. The author then proceeds with introductory modeling examples, behavioral and structural properties, three methods of analysis, subclasses of Petri nets and their analysis. In particular, one section is devoted to marked graphs, the concurrent system model most amenable to analysis. Introductory discussions on stochastic nets with their application to performance modeling, and on high-level nets with their application to logic programming, are provided. Also included are recent results on reachability criteria. Suggestions are provided for further reading on many subject areas of Petri nets     

Reliability block diagrams and “Petri” nets

A transformation algorithm is given to find a “Petri” net representation corresponding to a reliability block diagram. Several examples are given to illustrate the dynamic character of this representation. As an application we derive probability expressions from the “Petri” net representation.     

高职院校学习专业课程的方法探讨--以电子类专业为例

在当今时代高速发展的过程中,高职教育得到了人们广泛的重视。在高职课程体系之中,电子专业的课程是非常重要的课程。教师应在方法层面展开深入研究,确保每个学生潜在的积极性能够全部发挥出来,提升课程的整体水平。本文主要描述了高职教育中的电子专业课程如何培养学生兴趣的方法探讨。     

Modeling resource management in cellular systems using Petri nets

Modeling and analysis tools are essential for the design and evaluation of complex systems. This is particularly true for cellular systems, where, for instance, a variety of handoff, channel allocation, and data-transmission algorithms have been proposed. The capabilities of Petri nets (PNs) are used as a novel approach in the analysis of handoff, dynamic channel allocation (DCA), and cellular digital packet data resource management problems. The generalized stochastic PN (GSPN) models are obtained and analyzed as continuous-time Markov chains (MCs) derived from the reachability graphs. Solution of the MC results in performance indicators, which show the impacts of different algorithms on the system behavior