基于混合类间联想神经网络的光学模式识别

通过结合自联合模型与异联想模型，提出了一种混合类间联想神经网络的光学模式识别系统。在该神经网络中，输入模式矢量不仅通过自联想识别自身，还通过异联想识别配对矢量，因而提高了识别概率。与匹配滤波器光学模式识别系统相比，识别结果直接，系统简单可行。     

光学模式识别和人工智能处理器

介绍采用光学信息处理方法实现人工视觉功能的研究工作，以提取光学特生睡相关方法为主要特点的光学模式识别已经得到发展，但是还不能完全解决目标加比例尺，偏移，旋转，畸变，强干拢，部分阻挡，多目标等一系列问题。目前正努力发展光学人工智能处理器，包括符号处理，联想存储和处理，决策网络等。     

神经网络模式识别系统互连权重二值化研究

在增量算法的基础上，利用截断方法和蒙塔卡罗算法，对以四类飞行目标旋转投影作为学习样本的级联神经网络互连权重进行了二值优化处理，并用非学习样本进行了容错性检验，计算机木匠虱到了满意的结果。     

基于一维卷积神经网络的光纤周界入侵模式识别

针对干涉型分布式光纤传感系统,在通过Mel倒谱系数方法提取扰动信号频域特征进行模式识别的研究基础上,提出了一种基于一维卷积神经网络的光纤入侵模式识别方法.利用还原信号的分级阈值判断并提取入侵信号,有效减少了分帧方法导致的计算时间;构建了基于入侵信号傅里叶变换后的频域信息的一维卷积神经网络,自适应地提取扰动的信号频域特征...     

可编程光学击中击不中变换及其在模式识别中的应用

提出了一种利用击中击不中变换实现具有边缘噪声的模式的形态识别方法并给出计算模拟结果。利用一个非相干光学相关器，构成了一个实时可编程光学击中击不变处理器。演示了字符识别过程并给出了实验结果。     

仅用激发神经元的IPA神经网络模型及其光学实现

仅用激发神经元的IPA(Interpattern Association)型神经网络模型与既有激发又有抑制的IPA模型具有相似的性能。仅用激发神经元后,不需要光强的相减,这样可以较简单地实现全光神经网络系统,对相似的存储模式有较强的分辨力。此文提出了一套二维(8×8)光学神经网络实验系统,用透镜阵列实现互连,并给出了理论描述和光学实验结果。     

神经网络在声发射信号模式识别中的应用

介绍了人工神经网络中的BP网络、RBF网络、Hamming网络、BP－Hamming网络在声发射信号模式识别中的应用现状，并对这些方法的优缺点进行了比较。     

人工智能,神经网络与光学

从发展智能计算机的战略出发，介绍了人工神经网络的研究背景和发展简史，扼要说明了神经元的基本运算功能以及人工神经网络的构造和类型。从可学习性，大规模并行性以及联想和容错能力等方面，通过已有研究成果的实例，分析了人工神经网络作为一种新型智能信息处理系统所具有的主要特点。并从硬件实现的角度，阐明了人工神经网络与光学或光子技术的密切关系。     

一种改进型HOPFIELD神经网络模型及其单通道光学实现

提出一种改进型HOPFIELD神经网络模型。通过对存贮模式进行互补扩展,消除了存贮模式中0和1个数不等问题。利用扩展模式互补性和由扩展模式所形成的连接权的镜象对称性,在不增加神经元个数和连接权矩阵维数的情况下,提高了网络的存贮能力和容错能力。在此基础上设计了全正光学连接权矩阵,在单通道内实现了双极寻址,降低了光学系统的复杂性。     

局域互联神经网络的关联存储

基于全局互联的Hopfield模型,本文提出了局域互联关联存储的新概念.与全局互联相比,局域互联具有较小的关联矩阵,因而,有利于用现有的空间光调制器加以实现.同时,计算机模拟结果表明,它仍然具有全局关联存储的能力.     

Optical Learning Neural Network Using a Selfoc Microlens Array for Pattern Recognition

An optical system for learning neural networks with a 2-D architecture was constructed using a Selfoc microlens array. Using this system, we achieved pattern recognition of typed alphabet characters detected directly with a CCD camera. The system learned 4 characters according to a random search algorithm in order to avoid the difficulties and the costs of calculations of learning signals, optical alignments and addressing to the device which display the weight tensors.     

Influence of Blurred Ways on Pattern Recognition of a Scale-Free Hopfield Neural Network

We investigate the influence of blurred ways on pattern recognition of a Barabasi-Albert scale-free Hopfield neural network （SFHN） with a small amount of errors. Pattern recognition is an important function of information processing in brain. Due to heterogeneous degree of scale-free network, different blurred ways have different influences on pattern recognition with same errors. Simulation shows that among partial recognition, the larger loading ratio （the number of patterns to average degree P/ （k） ） is, the smaller the overlap of SFHN is. The influence of directed （large） way is largest and the directed （small） way is smallest while random way is intermediate between them. Under the ratio of the numbers of stored patterns to the size of the network PIN is less than O. 1 conditions, there are three families curves of the overlap corresponding to directed （small）, random and directed （large） blurred ways of patterns and these curves are not associated with the size of network and the number of patterns. This phenomenon only occurs in the SFHN. These conclusions are benefit for understanding the relation between neural network structure and brain function.     

Invariant Pattern Recognition Using Neural Networks Combined with Optical Wavelet Preprocessor

A novel pattern-recognition system that is invariant against scale-, position- and rotation-changes is proposed. The system is composed of an array of modular neural networks with local space-invariant interconnections (FELSI) [Appl. Opt. 29 (1990) 4790] and a multiwavelet transform preprocessor. The wavelet decomposition of two-dimensional patterns is optically realized by the VanderLugt correlator. To obtain the multiwavelet transforms simultaneously, we synthesize a correlation filter of multiwavelets using computer-generated holograms. The learning process of the FELSI with the techniques of additional noise and weight decay is shown to contribute to the invariant recognition of the system.     

基于数学形态谱和二维矢量分类网络的模式识别及二维矢量分类网络的光学实现

介绍一种基于数学形态谱和二维矢量分类网络的模式识别体系。数学形态谱相对于图像平移和旋转不变。建立了光学二维矢量分类网络，利用光学逻辑操作和最大值网络的循环操作，得到与输入图像最佳匹配的模式。     

Optoelectronic Thresholder for Pattern Recognition with Double Feedback Module

The present paper proposes a modification of a simple optoelectronic architecture (A. Bergeron et al.: Appl. Opt. 33 (1994) 1463) for carrying out optical thresholding operations. The threshold operation is achieved by means of a feedback loop. The setup is modified by inserting an attenuator adapted in each iteration to the total incident energy measured by an intensity detector. The proposed architecture does not need an additional light source, assures translation invariance and does not break the beam propagation path. The adaptive attenuator permits working under different lighting conditions (illumination, partially occluded objects, etc.). This kind of architecture is suitable for an optical pattern recognition task, optical neural network or optical associative memory. Application of the modified thresholder to the recognition task based on an optical correlator is reported.     

基于BP神经网络的诱发铀部件裂变信号特征分析及识别

在对诱发铀部件裂变信号的测量原理及特点分析的基础上,开展了基于BP神经网络的诱发铀部件裂变时间关联信号特征参量分析处理的研究工作。 采用无偏估计方法, 计算信号的自相关函数和互相关函数, 再利用比较法和导数法两种特征量提取方法, 提取出不同状态下裂变信号的特征参量, 借助于BP神经网络模式识别应用原理进行训练和预测。 理论分析和研究结果表明: 基于比较法和导数法获得的特征参量能较好地反映诱发铀部件裂变信号的特征; 用BP神经网络对裂变信号进行模式识别, 取得了较高的正确率, 验证了此方法的有效性和合理性。 The paper presents feature parameter analysis and processing in fission time dependent signal of induced uranium components based on BP Neural Networks through the analysis of the measuring principle and signal characteristics of induced uranium components fission signal. The auto correlation functions and cross correlation functions are calculated by using unbiased estimate, and then the feature parameters of fission signal in different status are extracted by using feature abstraction method, comparative method and derivative method, and then applied to training and prediction by means of BP neural networks based on pattern recognition. Theoretical analysis and the results show that, it is effective to obtain feature parameters of induced uranium component fission signal via comparative method and derivative method. UsingBP neural network to recognize patter of fission signal, we got good results that verified the effectiveness and reasonability of the method.     

Optical Learning Neural Network Using Photorefractive Waveguides

A model of an optical neural network with learning ability is proposed. We numerically evaluate the learning ability of the proposed network by using parameters determined by experiments. Adaptive connections between artificial neurons are implemented using photorefractive (PR) waveguides that can be optically modified by guided beams. The network consists of three layers and has bipolar weights within the limited range. The bipolar weight is encoded as the difference between optical power transmittances of signal beams in two channels of the PR waveguides. The adaptivity of the transmittance of PR waveguide is experimentally evaluated and is incorporated into the proposed network simulated in a computer. The proposed network is trained by a simplified local learning algorithm. Numerical results showed that the proposed three-layered network with six hidden neurons can solve the exclusive-or problem.     

洗牌型光电混合神经网络实验系统

在研究洗牌网局部互连光学实现问题的基础上 ,采用洗牌型图样间联想模型建立了具有完整的加权互连、求和、非线性处理及反馈功能的光电混合神经网络实验系统 ,进行了 8× 8数字样本的光学联想识别。实验结果证实了洗牌网理论的可行性和洗牌型图样间联想模型光学实现的优越性