一种用于图像二值化的细胞神经网络模型

本文提出了一种用于图像二值化的神经网络模型，它们称它为数字式细胞神经网络。它基于蔡少堂等提出的细胞神经网络概念，但采用了神经元离散时间的数字动力学技术，利用这个模型，只要通过简单的整数运算就可以并行高速地对灰度图像进行二值化，对于不同邻接和权值的选择得到了比传统二值化方法更自然的二值图像。另外，所提出的神经网络模型非常适合于数字ＶＬＳＩ实现。     

Recent VLSI neural networks in Japan

In this article, recent research activities on the development of electronic neural networks in Japan are reviewed. Most of the largest Japanese electronic companies have developed VLSI neural chips using analog, digital or optoelectronic circuits. They have run various neural networks on them. Recently, in Japan, digital approach becomes active. Several fully-digital VLSI chips for on-chip BP learning have been developed, and 2.3 GCUPS (Giga Connection Updates per Second) learning speed has already been attained. Although the numbers of neurons and synapses containable in single digital chips are small, a large neural network can be developed by cascading the chips. By cascading 72 chips, a fully interconnected PDM (Pulse Density Modulating) digital neural network system has been developed. The behavior of the system follows simultaneous nonlinear differential equations and the processing speed amounts to 12 GCPS (Giga Connections per Second).Intensive researches on analog and optoelectronic approaches have also been carried out in Japan. An analog VLSI neural chip attains 28 GCUPS on-chip learning speed and 1 TCPS (Tera Connections per Second) processing speed for Boltzmann machine with 1 bit digital output. For the optoelectronic approach, although the network size is small, 640 MCUPS BP learning speed has been attained.     

基于神经网络的4型FIR滤波器的优化设计

详细讨论了4型线性相位滤波器的幅频特性与正弦基函数神经网络算法的关系,分析了神经网络系统的稳定条件,给出了FIR滤波器优化设计实例。根据4型FIR滤波器的幅频响应特性,构造出一个相应的神经网络模型,并建立了FIR线性相位数字滤波器的神经网络算法。该算法通过训练神经网络权值,使设计的数字滤波器与希望得到的FIR线性相位滤波器的幅频响应之间的误差平方和最小化,从而获得FIR线性相位数字滤波器的脉冲响应。计算机仿真表明了该算法的有效性和优异性能。     

Nonlinear digital filters mimicking cellular neural networks

This work is motivated by the need forFaithful digital simulation of cellular neural networks (CNNs) that maintains most of their qualitative properties of stability and convergence. An interconnection of nonlinear digital filters mimicking behaviors of the analog CNNs is proposed, and the main properties are studied in detail. The discrete model obtained is proven to have the same convergence properties as the original analog network. The key to this development is the use of anAppropriate discretization scheme. Our discrete approximation to the nonlinear state-space representation of cellular neural networks is such that the Lyapunov function used to show convergence in analog cellular neural networks is still a Lyapunov function (when appropriately discretized) for our nonlinear digital filter network. This is in contrast to other digital simulations of CNNs, which have not been proven to preserve the convergence properties. The network of nonlinear digital filters so introduced thus adds another item to the catalog of digital filters obtained viaappropriate discretization of analog circuits, e.g., wave digital filters, orthogonal filters, and certain other of their more recently studied nonlinear counterparts.All authors were with the Stevens Institute of Technology, Hoboken, NJ, 07670 when this work was performed.Support from NSF grant MIP 9696176.     

低信噪比下的数字调制信号自动识别

提出了一种基于神经网络的数字调制信号识别。首先利用升余弦滤波器滤波,然后提取了5个用于识别的特征参数,利用神经网络分类器进行数字凋制识别。神经网络分类器采用了多层组合的神经网络分类器,不需要设定判决门限,而且在收敛速度、训练时间以及识别率方商都有很大改进。仿真结果表明,在信噪比大于4dB时,系统的正确识别率可达95％以上。这种低信噪比下快速有效的调制识别方法易于实时应用和工程实现。     

基于改进RBF神经网络的数字调制识别

针对数字调制信号自动识别中分类器的设计,通过将决策树的方法应用到RBF中心的确定中,解决了常用算法计算量大、收敛速度慢的问题,提高了网络的学习精度和训练速度,将其应用到常用的7种数字调制信号(2ASK,4ASK,BPSK,QPSK,2FSK,4FSK,16QAM)的自动识别中,取得了好的结果。经仿真表明,使用该方法构造的神经网络,具有易于构造、可理解性好、收敛速度快且构造的网络规模较小的特点,适于工程应用。     

Boolean neural network realization of an adder-subtractor cell

A great deal of interest has emerged recently in the field of Boolean neural networks. Boolean neural networks require far less training than the conventional neural networks and have a variety of applications. They are also strong candidates for VLSI design. In this paper, a technique for learning representation of an adder-subtractor cell has been proposed. The technique can be exploited for the VLSI design of an arithmetic unit for a pipelined digital computer.     

非理想信道多用户数字信号的盲分离

在一个信道上传送多个用户信号,可以大大提高信道的容量,本文讨论了非理想信道多和户数字信号的盲分离问题,利用天线阵,接收可以看作是由Ｎ个独立信号源激励的非线传输混合系统的输出;由于信道存在的码间干扰,混合矩阵的元素不是常数,而是一个线性子系统,针对这一情况,本文提出了一个盲分离器结构,首先将接收信号进行盲分离,然后利用基于ＡＲ模型的盲均衡器消除每一路输出信号的码间干扰,从而实现多用户信号物分离,语文     

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。     

BP神经网络在智能家庭网关中的应用研究

随着消费类电子产品技术的成熟,智能化家庭网络概念的深入人心,家庭网关在数字化家庭网络中将会扮演着越来越重要的角色.系统运用模糊神经网络技术提出了一种新型智能家庭网关,该网关运用基于误差反向传播算法优化的模糊神经网络技术,以神经网络输出结果和模糊化判决为依据对家居设备进行智能控制.同时还构造了室内空气质量分析系统,并将实验和仿真的精确度控制在0.1％内,证明了该系统的有效性和精确性.     

A Neural Network Approach for Signal Detection in Digital Communications

In this paper, we propose a new approach for signal detection in wireless digital communications based on the neural network with transient chaos and time-varying gain (NNTCTG), and give a concrete model of the signal detector after appropriate transformations and mappings. It is well known that the problem of the maximum likelihood signal detection can be described as a complex optimization problem that has so many local optima that conventional Hopfield-type neural networks fail to solve. By refraining from the serious local optima problem of Hopfield-type neural networks, the NNTCTG makes use of the time-varying parameters of the recurrent neural network to control the evolving behavior of the network so that the network undergoes the transition from chaotic behavior to gradient convergence. It has richer and more flexible dynamics rather than conventional neural networks only with point attractors, so that it can be expected to have much ability to search for globally optimal or near-optimal solutions. After going through a transiently inverse-bifurcation process, the NNTCTG can approach the global optimum or the neighborhood of global optimum of our problem. Simulation experiments have been performed to show the effectiveness and validation of the proposed neural network based method for the signal detection in digital communications.     

基于神经网络和DSP技术的离线数字识别系统

本文提出了一种基于神经网络的离线数字识别技术,采用神经网络来对图中的数字进行识别,在分析图像预处理对图像特征提取和识别影响的基础上,提出了一种基于目标的图像增强算法,该算法计算量小、实时性好,有效地解决了图像背景颜色差异和环境光线差异对图像特征提取和识别造成的影响。最后给出了系统基于DSP的硬件实现。     

有限环计算的数字式神经网络方法

本文提出一种用于有限环算术的数字式神比网络方法。它采用非对称的数字式神经网络结构，在整个矢量空间上具有唯一的平衡点，因而不存在计算误差。这种方法保持了神经网络的高度并行结构，能够实时完成有限环上的模运算。它还被应用于中国余数定理的实现。     

Neural network for the reliability analysis of simplex systems

A new approach to the reliability analysis, based on neural networks, is introduced in this paper. The reliability analysis of a simple nonredundant digital system, Simplex System, with repair is used to illustrate the neural network approach. The discrete-time Markov model of simplex systems is realized using feed-forward recursive neural network. The energy function and update equations for the weights of the neural network are estabilished such that the network converges to the desired reliability of the simplex system under design. The failure rate and repair rate, satisfying the desired reliability, are extracted from the neural weights at convergence. The obtained results are verified by the conventional approach.     

基于概率神经网络的数字音识别

本文主要利用概率神经网络和动态时间规整技术来实现数字音的识别研究。结论是在利用概率神经网络进行语音识别时可以达到比较高的识别率,此外动态时间规整函数的加入,解决了神经网络的模板规整问题。作为语音识别技术的基础,其中包含了小波的基础理论,语音的预处理,DTW技术,端点检测等基础技术。对于神经网络的加入,更加有利于深入了解神经网络这一新兴技术。     

Recurrent-neural-network-based implementation of a programmablecascaded low-pass filter used in stator flux synthesis ofvector-controlled induction motor drive

The concept of programmable cascaded low-pass filter for stator flux vector synthesis by ideal integration of stator voltages at any frequency was introduced by Bose and Patel. A new form of implementation of this filter is proposed that uses a combination of recurrent neural network trained by Kalman filter and a polynomial neural network. The proposed structure is simple, permits faster implementation by digital signal processor, and gives improved performance     

基于高阶累量与神经网络覆盖算法的数字调制识别

提出了一种把归一化四阶累量作为分类特征参数，应用神经网络覆盖算法进行分类的调制识别算法。对MFSK信号的三种归一化四阶累量进行了理论推导，对几种不同调制方式的数字通信信号的三种特征参数随信噪比的变化进行了仿真，证明了高阶累量不受高斯噪声影响的理论结果。最后应用神经网络覆盖算法进行分类识别，得到了比较好的识别结果。     

Analog neural programmable optimizers in CMOS VLSI technologies

Introduces a parallel switched-capacitor (SC) neural optimizer architecture and discusses area limitations due to the incorporation of programmability issues. Due to these limitations this architecture is only suitable for low dimension problems. A serial time-multiplexed architecture which allows digital control on the weight values with reasonable area figures is presented. A 3- mu m CMOS SC prototype demonstrating the concept of SC analog neural optimizers via an integrated circuit is discussed.<>     

Dynamic adaptation of quantization thresholds for soft-decision viterbi decoding with a reinforcement learning neural network

Two reinforcement learning neural network architectures which enhance the performance of a soft-decision Viterbi decoder used for forward error-correction in a digital communication system have been investigated and compared. Each reinforcement learning neural network is designed to work as a co-processor to a demodulator dynamically adapting the soft quantization thresholds toward optimal settings in varying noise environments. The soft quantization thresholds of the demodulator are dynamically adjusted according to the previous performance of the Viterbi decoder, with updates occurring in fixed intervals (every 200 decoded bits out of the Viterbi decoder.) To facilitate implementaiton in digital hardware, each weight of the neural network and related parameters are specified as binary numbers. Computer simulation results demonstrate that, on average, the performance of a Viterbi decoder on an AWGN channel with nonuniformly-spaced soft decision thresholds dynamically adjusted by these neural networks is better than the performance of a Viterbi decoder with uniformly-spaced thresholds. This approach may be used for a variety of other digital communication applications such as channel estimation, adaptive equalization, and signal acquisition.