Crossbar光交换网络

Crossbar网络是实现高速并行光学处理的一种最重要而有效的光交换网络结构。作为一种无阻塞网络,Crossbar网络具有简单性,易于实现控制,适合于构成光开关矩阵。总结和分析了近20多年来发展的Crossbar光交换网络,介绍了不同Crossbar光交换网络的原理、结构和性能,分析了Crossbar光交换网络的关键技术。目前光学互连网络的发展方向是实现集成大规模光互连。可以预见光学互连网络会朝着更加实用化的方向发展,并在其应用领域发挥越来越重要的作用。     

多准则图象重建的神经网络模型及实现

本文提出一种采用Ｈｏｐｆｉｅｌｅ神经网络（Ｈｏｐｆｉｅｌｄ Ｎｅｉｒａｌ Ｎｅｔｗｏｒｋ简称ＨＮＮ）优化的图象重建算法。将图象重建问题转化为ＨＮＮ优化问题,取重建图象的峰值函数最小以及原始投影与再投影之间的误差平方和最小作为图象重建的优化目标,作为能量函数构造连续型ＨＮＮ模型,由ＨＮＮ能量函数极小化可得到重建问题的优化解。这种方法具有简单、计算量小、收敛快、便于并行计算等特点。对照ＡＲＴ算法,用计算机模拟产生的无噪声投影数据检验新算法,验证了新算法的优越性。     

A New Architecture for Nonblocking Optical Switching Networks

With the current technology, all-optical networks require nonblocking switch architectures for building optical cross-connects. The crossbar switch has been widely used for building an optical cross-connect due to its simple routing algorithm and short path setup time. It is known that the crossbar suffers from huge signal loss and crosstalk. The Clos network uses a crossbar as building block and reduces switch complexity, but it does not significantly reduce signal loss and crosstalk. Although the Spanke's network eliminates the crosstalk problem, it increases the number of switching elements required considerably (to 2N ² - 2N). In this paper, we propose a new architecture for building nonblocking optical switching networks that has much lower signal loss and crosstalk than the crossbar without increasing switch complexity. Using this architecture we can build non-squared nonblocking networks that can be used as building block for the Clos network. The resulting Clos network will then have not only lower signal loss and crosstalk but also a lower switch complexity.     

Computerized tumor boundary detection using a Hopfield neuralnetwork

The authors present a new approach for detection of brain tumor boundaries in medical images using a Hopfield neural network. The boundary detection problem is formulated as an optimization process that seeks the boundary points to minimize an energy functional based on an active contour model. A modified Hopfield network is constructed to solve the optimization problem. Taking advantage of the collective computational ability and energy convergence capability of the Hopfield network, the authors' method produces the results comparable to those of standard “snakes”-based algorithms, but it requires less computing time. With the parallel processing potential of the Hopfield network, the proposed boundary detection can be implemented for real time processing. Experiments on different magnetic resonance imaging (MRI) data sets show the effectiveness of the authors' approach     

LANN AND ITS HETEROASSOCIATIVE MEMORY PROPERTIES

This paper provides a new architecture of neural network, called loop architecture neural network(LANN), and its learning rules. One of its features distinguished from other network, such as Hopfield and bidirectional associative memories, is that it can perform the associative memory among multiple categories. Analysis and simulated results have proved that it is an effective network with excellent convergence.     

A two-layer recurrent Neural Network based approach for overlay multicast

Overlay multicast has become one of the most promising multicast solutions for IP network, and Neutral Network（NN） has been a good candidate for searching optimal solutions to the constrained shortest routing path in virtue of its powerful capacity for parallel computation. Though traditional Hopfield NN can tackle the optimization problem, it is incapable of dealing with large scale networks due to the large number of neurons. In this paper, a neural network for overlay multicast tree computation is presented to reliably implement routing algorithm in real time. The neural network is constructed as a two-layer recurrent architecture, which is comprised of Independent Variable Neurons （IDVN） and Dependent Variable Neurons （DVN）, according to the independence of the decision variables associated with the edges in directed graph. Compared with the heuristic routing algorithms, it is characterized as shorter computational time, fewer neurons, and better precision.     

Bipartite graph design principle for photonic switching systems

Several attributes of a bipartite graph are exploited in designing switching systems. First, in a network based on bipartite graphs, no two paths are allowed to intersect at a vertex. This attribute is used to design a directional coupler-based photonic switching network with very low crosstalk. Since crosstalk is the most limiting factor in constructing a large directional-coupler-based photonic switching network, crosstalk reduction on the device and architecture levels is an important design issue. Secondly, broadcast, which is an intrinsic property of a bipartite graph (the same is always true with a crossbar representation), is used in designing multiconnection switching networks. Thirdly, it is shown that the nonplanar nature of bipartite graphs makes them well suited for designing three-dimensional free-space-transmission photonic switching systems     

分组交换网络调度算法概述

为了合理利用网络资源,提高网络吞吐率,降低通信时延,需要采取有效的调度算法实现输入端和输出端的匹配.基于VOQ的输入排队交换结构是当前分组交换网络最常用的结构.本文介绍了几种基于VOQ的调度算法:用于单级crossbar的PIM、iRRM和iSLIP算法,以及适用于三级Clos网络的RD和CDDR算法.对每种算法,介绍其基本原理和性能,以及与其他算法的区别.     

实现虚拟输出队列调度的神经网络方法

基于虚拟输出队列（VOQ）缓存的Crossbar交换结构,提出了一种Hopfield神经网络（HNN）控制的信元交换调度方法.通过选取合适的能量函数,并在其中采用一种新的队列优先级函数,实现了信元的高效交换控制.计算机模拟结果表明,该算法可以将吞吐率提高到0.998,信元丢失率大大降低,时延特性也有很大改善.     

Classification of multispectral images based on a fuzzy-possibilistic neural network

In this paper, a new Hopfield-model net based on fuzzy possibilistic reasoning is proposed for the classification of multispectral images. The main purpose is to modify the Hopfield network embedded with fuzzy possibilistic C-means (FPCM) method to construct a classification system named fuzzy-possibilistic Hopfield net (FPHN). The classification system is a paradigm for the implementation of fuzzy logic systems in neural network architecture. Instead of one state in a neuron for the conventional Hopfield nets, each neuron occupies 2 states called membership state and typicality state in the proposed FPHN. The proposed network not only solves the noise sensitivity fault of Fuzzy C-means (FCM) but also overcomes the simultaneous clustering problem of possibilistic C-means (PCM) strategy. In addition to the same characteristics as the FPCM algorithm, the simple features of this network are clear potential in optimal problem. The experimental results show that the proposed FPHN can obtain better solutions in the classification of multispectral images.     

Performance evaluation of input-buffered replicated banyan networks

Input-buffered replicated networks are considered for broadband switching applications. They are characterized by many design parameters such as the replication factor, the traffic management policy, and input buffer location and length. To show the influence of these parameters on switching performance, an analytical model is defined based on a Markov chain representation of the input buffer. This model is suitable for application to input buffered architecture having different routing network choices. The results, expressed in terms of throughput, packet delay, and packet loss probability, outline the performance improvements with respect to other well-known networks with input buffers, such as banyan and crossbar, reached through the flexibility offered by this architectural solution     

Resource allocation for statistical quality of service provision in buffered crossbar switches

The buffered crossbar switch is a promising switching architecture that plays a crucial role for providing quality of service (QoS) in computer networks. Sufficient amount of resources—bandwidth and buffer space—must be allocated in buffered crossbar switches for QoS provision. Resource allocation based on deterministic QoS objectives might be too conservative in practical network operations. To improve resource utilization in buffered crossbar switches, we study the problem of resource allocation for statistical QoS provision in this paper. First, we develop a model and techniques for analyzing the probabilistic delay performance of buffered crossbar switches, which is described by the delay upper bound with a prescribed violation probability. Then, we determine the required amounts of bandwidth and buffer space to achieve the probabilistic delay objectives for different traffic classes in buffered crossbar switches. In our analysis, we apply the effective arrival envelope to specify traffic load in a statistical manner and characterize switch service capacity by using the service curve technique. Instead of just focusing on one specific type of scheduler, the model and techniques developed in this paper are very flexible and can be used for analyzing buffered crossbar switches with a wide variety of scheduling algorithms. Copyright © 2007 John Wiley & Sons, Ltd.     

基于多层前馈神经网络的二维自适应消噪方法

提出了一种基于多层前馈神经网络对带噪声样本进行二维去噪声建模的新方法,分析了神经网络的结构和原理并改进了反向传播训练算法,从理论上进行了论证。仿真结果表明此方法能较好地实现噪声消除,相对于传统的线性噪声对消器和基于Hopfield网络的消噪方法,具有更优越的性能,保持了原始信号的完整性,达到了有效抑制噪声的目的。     

具有纵横输入互连方式和缓冲结构的递归Knockout交换网络

本文提出了具有纵横输入（ＣｒｏｓｂａｒＩｎｐｕｔ）互连方式和输入缓冲（ＩｎｐｕｔＢｕｆｅｒｅｄ）结构的递归Ｋｎｏｃｋｏｕｔ交换网络（ＣＩＢＲＫＳ）．通过采用纵横输入互连方式可减少内部小交换单元的数目,并可使信元传送顺序不会受群输出端口数目的影响．而通过在每个输入端放置缓冲器可在保持丢失率性能不变的情况下,可使整个交换网络的级数减少,从而也就减少了信元在群网络中的传输时延．另外,在该结构中,通过把信元滤址的功能从每个小交换单元中提取出来放在每个输入端口,又进一步减少了小交换单元的功能．通过比较,我们认为,作为大规模ＡＴＭ交换网络结构,ＣＩＢＲＫＳ结构比传统的ＲＫＳ结构具有较好的性能／复杂度特性．     

A Context-Sensitive Technique for Unsupervised Change Detection Based on Hopfield-Type Neural Networks

In this paper, we propose a context-sensitive technique for unsupervised change detection in multitemporal remote sensing images. This technique is based on a modified Hopfield neural network architecture designed to model spatial correlation between neighboring pixels of the difference image produced by comparing images acquired on the same area at different times. Each spatial position in the considered scene is represented by a neuron in the Hopfield network that is connected only to its neighboring units. These connections model the spatial correlation between neighboring pixels and are associated with a context-sensitive energy function that represents the overall status of the network. Change detection maps are obtained by iteratively updating the output status of the neurons until a minimum of the energy function is reached and the network assumes a stable state. A simple heuristic thresholding procedure is presented and adopted for initializing the network. The proposed change detection technique is unsupervised and distribution free. Experimental results carried out on two multispectral and multitemporal remote sensing images confirm the effectiveness of the proposed technique     

ATM switching architectures for wafer-scale integration

This paper proposes the use of wafer-scale integration (WSI) technology for ATM switching systems and presents two different switching architectures specifically designed for WSI. WSI is particularly useful for switching networks since the interconnection lengths are minimized when the entire network is laid out on a single semiconductor wafer. We propose a defect-tolerant multipath buffered crossbar (MBC) with an expandable structure which can easily be scaled up or down according to the choice of wafer size. We also design an ATM-based Manhattan-street network (MSN) as an alternative architecture, suitable for wafer-scale implementation. We compare the two architectures from different standpoints such as performance, defect-tolerance, delay, practicality, testability, complexity, yield, and area     

离散Hopfield神经网络的PWM型脉冲流技术实现

研究了离散Hopfield神经网络的PWM(脉冲宽度调制)型脉冲流技术实现。利用MOS开关管和电压比较器实现了离散Hopfield神经网络，并提出了利用离散Hopfiled神经网络实现自联想记忆时相应的PWM型脉冲流电路。所提出的电路结构简单，易于芯片间通讯及系统扩展。     

基于神经网络密码的图像加密

利用离散Hopfrield神经网络生成的序列密码,对图像信号进行加密和解密的实验研究表明,该网络可模拟复杂非线性函数,使输出序列的周期性、0与1平衡性和序列相关性等均满足序列密码设计要求,而且并行运算速度快,有利于数字电路实现.     

Superresolution algorithms for a modified Hopfield neural network

The authors describe the implementation of a superresolution (or spectral extrapolation) procedure on a neural network, based on the Hopfield (1982) model. They show the computational advantages and disadvantages of such an approach for different coding schemes and for networks consisting of very simple two-state elements as well as those made up of more complex nodes capable of representing a continuum. It is demonstrated that, with the appropriate hardware, there is a computational advantage in using the Hopfield architecture over some alternative methods for computing the same solution. The relationship between a particular mode of operation of the neural network and the regularized Gerchberg (1974) and Papoulis (1975) algorithm is also discussed     

Hopfield Neural Network Approach to Clustering in Mobile Radio Networks

ＨｏｐｆｉｅｌｄＮｅｕｒａｌＮｅｔｗｏｒｋＡｐｐｒｏａｃｈｔｏＣｌｕｓｔｅｒｉｎｇｉｎＭｏｂｉｌｅＲａｄｉｏＮｅｔｗｏｒｋｓＪｉａｎｇＹａｎ；ＬｉＣｈｅｎｇｓｈｕ（ＮｏｒｔｈｅｒｎＪｉａｏｔｏｎｇＵｎｉｖｅｒｓｉｔｙ，Ｂｅｉｊｉｎｇ１０００４４）Ａｂ...