求解超定线性方程组L1—范数最优解的神经网络方法

基于线性规划对偶理论，本文给出一种求解超定性方程组Ｌ１－范数解的神经网络方法。这一方法由两部分组成，首先利用ＬＳＳＭ神经网络求出Ｌ１问题的近似对偶解，然后利用改进的Ｔ－Ｈ网络求Ｌ１－问题的解，当参数选择适当时，Ｔ－Ｈ网络的全局渐近稳定点就是问题的精确解，模拟试验也表明了这一方法的可行性。     

采用HDSL的网络接入技术

ＨＤＳＬ（高速率数据用户环路）是目前利用铜线进行高速数据传输的比较理想的方法。ＨＤＳＬ按其用户接口类型来分，常见的有标准Ｅ１接口和１０ＢＡＳＥ－Ｔ以太网接口两类，用它们可以构成几种不同的网络拓朴结构。     

宽视角TFT—LCD的混合转换方式

本文就可获得宽视角ＴＦＴ－ＬＣＤ的混合转换（ＨＳ）方式提出论证，在新开发的ＨＳ方式中，象素电采是用来作用于垂直和水平方向的电场，这对高显示性能及宽视角极为有效。我们采用ＨＳ方法开发出了高性能３６ｃｍ的ＴＦＴ－ＬＣＤ监示器。     

HDSL技术和速度可调的接口电路

ＨＤＳＬ作为利用铜双绞线进行Ｅ１／Ｔ１数据传输的比较有效方法，已被大量用户采用。随着子速率专用线的大量使用，实现ＮＸ６４Ｋ子速率数据传输的ＨＤＳＬ设备也被用户普遍接受。本文对ＨＤＳＬ技术作了介绍，对ＨＤＳＬ系统作了分类，并对各类ＨＤＳＬ系统的结构，及其相应ＮＸ６４Ｋ速率可调整接口电路，分别做了详细介绍。     

R＆S测试车后处理软件ROSEVAL的使用经验

目前,国内许多省市移动通信局都先后购买了德国Ｒｏｈｄｅ民Ｓｃｈｗａｒｚ公司的ＴＳ９９５５测试系统。该系统集成了先进的网络质量测试软件ＴＳＳＸ—Ｋ１及其后处理软件ＲＯＳＥＶＡＬ、网络干扰测试软件ＰＣＳＤ－Ｋ１和信道脉冲响应测试软件ＰＣＳＤ－Ｋ２。其中,ＴＳ５Ｘ－Ｋ１提供了强大的网络实时测试、显示能力,而ＲＯＳＥ－ＶＡＬ则为从ＴＳＳＸ－Ｋ１测试软件中取出的测试数据提供了更为强大的后处理能力和非常优秀的可视化平台。在ＲＯＳＥＶＡＬ软件窗口中能够同时打开多个地图（Ｍａｐ）、表格（Ｔａｂｌｅ）以及二维图表…     

1．8GHz下功率密度为2．8W／mm的4H－SiC MES FET

１．８ＧＨｚ下功率密度为２．８Ｗ／ｍｍ的４Ｈ－ＳｉＣＭＥＳＦＥＴ据《ＩＥＥＥＥ．Ｄ．Ｌ．》第１５卷第１０期报道，ＣｈａｒｌｅｓＥ．Ｗｅｉｔｚｅｌ等已研制成一种４Ｈ－ＳｉＣＭＥＳＦＥＴ。采用４Ｈ－ＳｉＣ是由于它比６Ｈ－ＳｉＣ高出两倍的电子迁移率。器件的...     

离子注入和退火技术

离子注入和退火技术（索尼）野口隆１前言多晶硅ＴＦＴ已在ＬＣＤ、ＬＳＩ存储器两个领域中成为重要的开关元件。对于６００℃以上工艺，离子注入和退火技术就成了提高ＴＦＴ性能的最重要的工艺。氢化非晶硅（ａ－Ｓｉ：Ｈ）ＴＦＴ已作为有源矩阵用于大面积显示（ＬＣＤ）...     

模拟电路故障诊断L1估计及其神经网络解法

基于精确罚函数法，提出了新的求解Ｌ１范数问题最优解的神经网络方法，它避免了Ｋｅｎｎｅｄｙ和Ｃｈｕａ网络罚因子较大时性态变坏问题。对Ｂａｎｄｌｅｒ提出的模拟电路故障诊断Ｌ１范数法进行了改进，将线性约束Ｌ１问题转化为非线性约束Ｌ１问题，并用新的神经网络方法求解，计算量小。     

基于DMT的HDSL／ADSL系统中的回波抵消技术

高比特率数字用户环路是在光纤用户网普及之前向用户提供宽带业务的一种过渡手段。ＤＭＴ（离散多音频调制）是一种多载频调制，由于性能优越，被广泛应用于ＨＤＸＳＬ和ＡＤＳＬ系统中。采用加波抵消的方法，可以提高系统传输速率、增加传输距离。本文着 基于ＤＭＴ的ＨＤＳＬ和ＡＤＳＬ系统中的回波抵消技术－－ＴＡＦＤＥＣ方法，即将频域的回波抵消器（ＥＣ）和时域的回波合成器（ＣＥＳ）结合起来，以达到减少运算量，降低复杂     

SunSet xDSL用于数字用户线测试

Ｓｕｎｒｉｓｅ公司推出的数字用户线测试仪ＳｕｎＳｅｔ ｘＤＳＬ综合了数字多用表、时域反射计、频谱分析仪功能以及内置ＡＤＳＬ／ＨＤＳＬ调制解调器模块,仅重１．３千克。利用它可通过单端测量、主从机测量和ＡＴＵ－Ｃ／Ｒ仿真等方法,进行开通前线路质量确认性测试、传输质量测试以及故障定位测试等。     

A Neutral-Type Delayed Projection Neural Network for Solving Nonlinear Variational Inequalities

A neutral-type delayed projection neural network is proposed to deal with nonlinear variational inequalities. Compared with the existing delayed neural networks for linear variational inequalities, the proposed approach apparently has the larger application domain. By the theory of functional differential equation, a delay-dependent sufficient stability condition is derived. This stability condition is easily checked, and can guarantee that the proposed neural network is convergent to the solution of nonlinear variational inequality problem exponentially, which improves the existing stability criteria for the neutral-type delayed neural network. Moreover, many related problems, such as the projection equation and optimization problems, can also be dealt with by the proposed method. Finally, simulation examples are given to illustrate the satisfactory performance of the proposed method.      

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。     

Parametric signal restoration using artificial neural networks

The problem of parametric signal restoration given its blurred/nonlinearly distorted version contaminated by additive noise is discussed. It is postulated that feedforward artificial neural networks can be used to find a solution to this problem. The proposed estimator does not require iterative calculations that are normally performed using numerical methods for signal parameter estimation. Thus high speed is the main advantage of this approach. A two-stage neural network-based estimator architecture is considered in which the vector of measurements is projected on the signal subspace and the resulting features form the input to a feedforward neural network. The effect of noise on the estimator performance is analyzed and compared to the least-squares technique. It is shown, for low and moderate noise levels, that the two estimators are similar to each other in terms of their noise performance, provided the neural network approximates the inverse mapping from the measurement space to the parameter space with a negligible error. However, if the neural network is trained on noisy signal observations, the proposed technique is superior to the least-squares estimate (LSE) model fitting. Numerical examples are presented to support the analytical results. Problems for future research are addressed     

Unstructured PEEC formulation by dual discretization

This letter presents a new lumped parameter approach for the solution of the electromagnetic problem of a system of conductors lying in a homogeneous region. By exploiting duality relations between two systems of meshes, an equivalent network of lumped parameters is obtained. This approach is conceptually equivalent to the partial element equivalent circuit formulation but it can overcome the limits imposed by a regular discretization present in its original version. Details about computation of lumped parameters and definition of equivalent network are given. Results obtained on two configurations referenced in the literature are finally discussed.     

Stable identification of nonlinear systems using neural networks: theory and experiments

This paper presents an approach for stable identification of multivariable nonlinear system dynamics using a multilayer feedforward neural network. Unlike most of the previous neural network identifiers, the proposed identifier is based on a nonlinear-in-parameters neural network (NLPNN). Therefore, it is applicable to systems with higher degrees of nonlinearities. Both parallel and series-parallel models are used with no a priori knowledge about the system dynamics. The method can be considered both as an online identifier that can be used as a basis for designing a neural network controller as well as an offline learning scheme for monitoring the system states. A novel approach is proposed for the weight updating mechanism based on the modification of the backpropagation (BP) algorithm. The stability of the overall system is shown using Lyapunov's direct method. To demonstrate the performance of the proposed algorithm, an experimental setup consisting of a three-link macro-micro manipulator (M/sup 3/) is considered. The proposed approach is applied to identify the dynamics of the experimental robot. Experimental and simulation results are given to show the effectiveness of the proposed learning scheme.     

Subgradient-Based Neural Networks for Nonsmooth Convex Optimization Problems

This paper develops a neural network for solving the general nonsmooth convex optimization problems. The proposed neural network is modeled by a differential inclusion. Compared with the existing neural networks for solving nonsmooth convex optimization problems, this neural network has a wider domain for implementation. Under a suitable assumption on the constraint set, it is proved that for a given nonsmooth convex optimization problem and sufficiently large penalty parameters, any trajectory of the neural network can reach the feasible region in finite time and stays there thereafter. Moreover, we can prove that the trajectory of the neural network constructed by a differential inclusion and with arbitrarily given initial value, converges to the set consisting of the equilibrium points of the neural network, whose elements are all the optimal solutions of the primal constrained optimization problem. In particular, we give the condition that the equilibrium point set of the neural network coincides with the optimal solution set of the primal constrained optimization problem and the condition ensuring convergence to the optimal solution set in finite time. Furthermore, illustrative examples show the correctness of the results in this paper, and the good performance of the proposed neural network.      

一种求解带等式约束的二次规划问题的新神经网络模型

本文提出了一种新的神经网络模型用以求解带等式约束的二次规划问题。本模型大大改进了Shenguei zhang等人(1992)给出的二阶神经网络。后者的结构复杂,且只适用于求解具有唯一最优解的情况,而不能求解最优解为无界集合的情形。与它相比,本文提出的新神经网络模型不仅能够精确求解具有唯一最优解的情况,而且还能实时求解最优解集合为无界的情况,此外,在结构上也大为简化,易于电路实现。     

Blind restoration of nonlinearly mixed signals using multilayer polynomial neural network

It is shown how nonlinearly mixed signals can be retrieved uniquely by using a novel approach based on signal restoration methodology rather than the conventional technique of mere signal separation. A new mathematical model of the nonlinear mixing system has been developed culminating in the formulation of a stable unique inverse solution, which has an identical structure to the multilayer neural network. In addition, it is shown how the optimum framework for the nonlinear demixing system can be obtained directly from the derived mixing model. It is further shown how the proposed schemes using the multilayer polynomial neural network (PNN) can be utilised to acquire the desired solution. Moreover, the corresponding learning algorithm based on the generalised stochastic gradient descent method combined with a modified genetic algorithm (GA) has been developed to yield a novel and more effective approach in updating the parameters of the PNN. Both synthetic and real-time simulations have been conducted to verify the efficacy of each proposed scheme.     

A Neural Network-Based Blind Multiuser Receiver for DS-CDMA Communication Systems

The Universal Mobile Telecommunications System (UMTS) which is based on Wideband-Code Division Multiple Access (W-CDMA) techniques is one of the most important broadband wireless communication systems. Adaptive Blind Multiuser Detection was widely considered for mobile receivers. The main drawback of this approach is that it achieves the optimum solution after a certain number of bit times. This paper deals with a new neural network approach in order to reduce the convergence time in different application environments. In particular, a modified Kennedy-Chua neural network, based on the Hopfield model is proposed. The neural network stability was investigated by means of a suitable analytical approach, while the performance of the proposed receiver scheme was derived by means of computer simulations. The numerical results shown in this paper highlight a fast convergence behavior of the proposed scheme, in particular under multipath-fading conditions. This revised version was published online in July 2006 with corrections to the Cover Date.     

用退火型神经网络估计多个非相干源的迭加正弦信号参量＊

基于模拟退火方法和线性规划神经网络,本文提出了一种新的参数估计方法——退火型神经网络计算方法,并将其应用于进行叠加正弦信号参量的估计,通过构造相应的模拟电路系统,该方法可获得估计问题的实时解。模拟实验结果显示了该神经网络方法进行平面波到达方向估计与跟踪的优良性能。