Low bit-rate video compression with neural networks and temporalsubsampling

In this paper we describe a novel neural network technique for video compression, using a “point-process” type neural network model we have developed which is closer to biophysical reality and is mathematically much more tractable than standard models. Our algorithm uses an adaptive approach based upon the users' desired video quality Q, and achieves compression ratios of up to 500:1 for moving gray-scale images, based on a combination of motion detection, compression, and temporal subsampling of frames. This leads to a compression ratio of over 1000:1 for full-color video sequences with the addition of the standard 4:1:1 spatial subsampling ratios in the chrominance images. The signal-to-noise ratio ranges from 29 dB to over 34 dB. Compression is performed using a combination of motion detection, neural networks, and temporal subsampling of frames. A set of neural networks is used to adaptively select the desired compression of each picture block as a function of the reconstruction quality. The motion detection process separates out regions of the frame which need to be retransmitted. Temporal subsampling of frames, along with reconstruction techniques, lead to the high compression ratios     

神经网络在图像编码中的应用

神经网研究的再度兴起及其在图像编码中的应用，开辟了图像压缩的新途径。本文论述了用于图像编码的神经网络模型、算法、应用效果及进展，对该领域尚未解决的一些基本理论问题，如神经网络实现图像数据压缩的机理，基于神经网络图像编码方法的分类等进行了探讨。最后，展望了需要进一步研究的方向。     

神经网络在通信中的应用

神经元网络的应用研究是近年来的一个研究热点。研究表明,在诸如自适应信号处理、最佳接收、纠错编码、压缩编码、模式识别、通信网等通信领域中,神经元网络可望得到广泛的应用。本文综述了几种神经元网络在通信中的应用研究工作。     

一种改进的LeNet网络

针对卷积神经网络中存在的学习效率低、收敛速度慢、训练时间长等问题,文中提出一种改进的LeNet卷积神经网络模型。该模型使用卷积核大小为3,步幅为2的卷积层代替原有的池化层,并在每层激活函数之前添加批量归一化层。在Mnist和Cifar-10数据集上放入实验证明,相比于传统的LeNet网络,所提出的卷积神经网络提高了分类准确率,并且具有更快的收敛速度及更短的训练时间。     

符号-神经网络系统的研究

符号推理系统已成功地用于过程控制、医疗诊断等众多领域.但是,仍有一些问题仅仅使用纯符号技术是难以解决的.例如,人们运用自如的视觉功能等.在许多这类领域中,基于人工神经网络的系统大有希望。然而由于目前的神经网络学习效率低、训练时间长等问题,使得神经网络的实际应用受到很大影响.本文试图通过知识的引入,提高神经网络系统的学习效率和泛化能力.其方法是:(1)网络的分解(decomposition ofnetworks);(2)规则-注入提示(rule-injection hints)。这两种方法起着符号系统中加入规则或定义算法的类似作用。本文通过对学习单调函数的分析,总结出什么样的函数容易学习以及什么样的函数能给出有效的提示.最后,本文结合机器人手臂控制系统的设计,验证了其方法是可行的.     

Banyan网输入输出排队的神经网络调度及其实现

Ｂａｎｙａｎ网是一种多级互联网络，它广泛地应用在ＡＴＭ交换结构中．Ｂａｎｙａｎ网输入排队的神经网络调度方法已有文章提出，但其硬件实现比较复杂．本文提出了一种Ｂａｎｙａｎ网输入输出排队的神经网络调度方法，它的硬件实现容易．计算机模拟结果表明，该调度方法是非常有效的．在此，还给出了该系统的硬件实现方法．     

Daugman's Gabor transform as a simple generative back propagation network

Much work has been performed on learning mechanisms for neural networks. A particular area of interest has been the use of neural networks for image processing problems. Two important pieces of work in this area are unified. An architecture and learning scheme for neural networks called generative back propagation has been previously developed and a system for image compression and filtering based on 2-D Gabor transformations which used a neural network type architecture described. Daugman's procedure is exactly replicated, a procedure which used a four layer neural network as a two-layer generative back propagation network with half of the units. The GBP update rule is shown to perform the same change as Daugman's rule, but more efficiently.<>     

S-transform-based intelligent system for classification of power quality disturbance signals

In this paper, a new approach is presented for the detection and classification of nonstationary signals in power networks by combining the S-transform and neural networks. The S-transform provides frequency-dependent resolution that simultaneously localizes the real and imaginary spectra. The S-transform is similar to the wavelet transform but with a phase correction. This property is used to obtain useful features of the nonstationary signals that make the pattern recognition much simpler in comparison to the wavelet multiresolution analysis. Two neural network configurations are trained with features from the S-transform for recognizing the waveform class. The classification accuracy for a variety of power network disturbance signals for both types of neural networks is shown and is found to be a significant improvement over multiresolution wavelet analysis with multiple neural networks.     

Hopfield型联想记忆神经网络一种新的分析方法

本文通过定义一种新的能量函数，分析了Ｈｏｐｆｉｅｌｄ型神经网络的渐近稳定性与联想记忆问题，得到了四组保证网络平衡点是渐近稳定平衡点的充分条件，应用这些条件，便可设计联想记忆神经网络，文中给出了应用这些结论设计联想记忆神经网络的实验结果及分析。     

Global asymptotic and robust stability of recurrent neural networks with time delays

In this paper, two related problems, global asymptotic stability (GAS) and global robust stability (GRS) of neural networks with time delays, are studied. First, GAS of delayed neural networks is discussed based on Lyapunov method and linear matrix inequality. New criteria are given to ascertain the GAS of delayed neural networks. In the designs and applications of neural networks, it is necessary to consider the deviation effects of bounded perturbations of network parameters. In this case, a delayed neural network must be formulated as a interval neural network model. Several sufficient conditions are derived for the existence, uniqueness, and GRS of equilibria for interval neural networks with time delays by use of a new Lyapunov function and matrix inequality. These results are less restrictive than those given in the earlier references.     

Qualitative analysis for recurrent neural networks with linear threshold transfer functions

Multistable networks have attracted much interest in recent years, since multistability is of primary importance for some applications of recurrent neural networks where monostability exhibits some restrictions. This paper focuses on the analysis of dynamical property for a class of additive recurrent neural networks with nonsaturating linear threshold transfer functions. A milder condition is derived to guarantee the boundedness and global attractivity of the networks. Dynamical properties of the equilibria of two-dimensional networks are analyzed theoretically, and the relationships between the equilibria features and network parameters (synaptic weights and external inputs) are revealed. In addition, the sufficient and necessary conditions for coexistence of multiple equilibria are obtained, which confirmed the observations in with a cortex-inspired silicon circuit. The results obtained in this paper are applicable to both symmetric and nonsymmetric networks. Simulation examples are used to illustrate the theory developed in this paper.     

BP算法的改进在Matlab的实现研究

利用Matlab中的神经网络工具箱提供的丰富网络学习和训练函数,对BP网络和BP算法的优化方素进行仿真．得到较优的BP算法。     

NEURAL MEMORY MODEL AND ITS PIECEWISE-LINEAR NETWORK REALIZATION

This paper studies the neural networks by means of neural functions.The memoryfunction of neural networks is investigated and its mathematical model is given.The model issynthesized by a piecewise-linear resistive network which exhibits many properties of artificialneural network such as parallelism,real-time processing capability,distribution,adaptation.Inaddition,all parameters of the network are expressed analytically by the patterns and featureswhich are memorized in the network.     

Routing in optical multistage interconnection networks: a neuralnetwork solution

There has been much interest in using optics to implement computer interconnection networks. However, there has been little discussion of any renting methodologies besides those already used in electronics. In this paper, a neural network routing methodology is proposed that can generate control bits for a broad range of optical multistage interconnection networks (OMIN's). Though we present no optical implementation of this methodology, we illustrate its control for an optical interconnection network. These OMIN's can be used as communication media for distributed computing systems. The routing methodology makes use of an artificial neural network (ANN) that functions as a parallel computer for generating the routes. The neural network routing scheme can be applied to electrical as well as optical interconnection networks. However, since the ANN can be implemented using optics, this routing approach is especially appealing for an optical computing environment. Although the ANN does not always generate the best solution, the parallel nature of the ANN computation may make this routing scheme faster than conventional routing approaches, especially for OMIN's that have an irregular structure. Furthermore, the ANN router is fault-tolerant. Results are shown for generating routes in a 16×16, 3-stage OMIN     

基于超像素提取和级联匹配的灰度图像自动彩色化

针对目前卷积神经网络未能充分提取图像的浅层特征信息导致近红外图像彩色化算法存在结果图像局部区域误着色及网络训练不稳定导致结果出现模糊问题,提出了一种新的生成对抗网络方法用于彩色化任务。首先,在生成器残差块中引入自行设计的空洞全局注意力模块,对近红外图像的每个位置理解更加充分,改善局部区域误着色问题;其次,在判别网络中,将批量归一化层替换成梯度归一化层,提升网络判别性能,改善彩色化图像生成过程带来的模糊问题;最后,将本文算法在RGB_NIR数据集上进行定性和定量对比。实验表明,本文算法与其他经典算法相比能充分提取近红外图像的浅层信息特征,在指标方面,结构相似性提高了0.044,峰值信噪比提高了0.835,感知相似度降低了0.021。     

基于遗传算法的BP神经网络在图像压缩中的应用

以神经网络和遗传算法为代表的进化算法都基于智能信息处理的理论,但是各自都存在一些缺陷.设计并实现了基于遗传算法的BP神经网络算法BP-GA,该算法将遗传算法和BP算法相结合,用基于实数编码的遗传算法优化神经网络的权值后,应用于图像压缩.实验证明,利用此混合神经网络进行图像压缩,压缩比高,图像恢复质量效果好.     

基于HBF神经网络的自适应观测器

传统的RBF(Radial Basis Function)神经元基函数通常把高斯类型与单一宽度作为每个神经元的激活函数,这些特性限制了网络神经元的性能,特别是在处理复杂的非线性建模问题上.为了克服这个限制,本文应用了具有类似RBF网络,但激活函数不同-超基函数HBF(Hyper Basis Function)的网络.结合RBF网络,分析了HBF网络的结构、基函数形式及基函数对网络的影响,利用决策树算法计算了网络中心.在此基础上,提出了一种基于HBF神经网络的自适应观测器设计方法,并通过引入Lyapunov函数,证明了这种观测器设计方法的稳定性;最后通过仿真验证了这种HBF神经网络观测器能很好地观测系统的状态值.     

小波神经网络在电磁无损检测中的应用

在基于正交小波变换的小波神经网络模型构造的基础上,选取B-小波为小波基提出了一种小波神经网络新算法。通过选取典型训练样本集的方法提高了该小波神经网络诊断的准确性,并运用该小波神经网络对钢丝绳电磁无损检测信号进行了压缩与重构,试验结果证明了小波神经网络能够较为理想地完成缺陷信号的智能化检测,采用小波神经网络算法比传统的断丝识别方法准确率提高了很多。     

LFM-M码信号旁瓣抑制技术

为了进一步提高雷达的探测性能,设计了线性调频–二相码(LFM-M)混合调制脉冲压缩信号。采用分类比较的方法,研究了反向传播网络、Elman网络和径向基函数(RBF)网络等3种典型神经网络在其脉冲压缩中的应用,设计了网络的结构,分析了网络的算法。通过仿真和对脉冲压缩输出性能的研究得出,采用RBF神经网络对LFM-M码信号进行脉冲压缩,网络具有较快的收敛速度和较好的数值稳定性,可获得60 d B左右的输出主旁瓣比。     

RESEARCHES ON THE STABILITIES OF ANALOG ELECTRONIC NEURAL NETWORKS

A new method for analyzing the stabilities of analog electronic neural networks ispresented.The energy functions with clear physical meaning are derived by introducing the staticequivalent circuit models,which has expanded the Tellegen Theorem for application on circuitanalysis.The method used to derive the energy functions of nets from first order differentialequations is valid for all first order continuous autonomous systems.The stability analysis ofcellular neural networks is made by the use of the stationary cocontent theorem.Some resultsare instructive for the network implementation on circuits.