Second-order asymmetric BAM design with a maximal basin of attraction

Bidirectional associative memory (BAM) generalizes the associative memory (AM) to be capable of performing two-way recalling of pattern pairs. Asymmetric bidirectional associative memory (ABAM) is a variant of BAM relaxed with connection weight symmetry restriction and enjoys a much better performance than a conventional BAM structure. Higher-order associative memories (HOAMs) are reputed for their higher memory capacity than the first-order counterparts. The paper concerns the design of a second-order asymmetric bidirectional associative memory (SOABAM) with a maximal basin of attraction, whose extension to a HOABAM is possible and straightforward. First, a necessary and sufficient condition is derived for the connection weight matrix of SOABAM that can guarantee the recall of all prototype pattern pairs. A local training rule which is adaptive in the learning step size is formulated. Then derived is a theorem, designing a SOABAM further enlarging the quantities required to meet the complete recall theorem will enhance the capability of evolving a noisy pattern to converge to its association pattern vector without error. Based on this theorem, our algorithm is also modified to ensure each training pattern is stored with a basin of attraction as large as possible.     

基于混沌神经网络的电机故障诊断

采用全局耦合混沌神经网络模型，每个神经元的动力学行为由反对称立方映像表示。采用Hebb算法设计网络的连接权值矩阵．将记忆模式的回忆过程转化为耦合系统中参数演变的过程，从而实现了混沌神经网络的联想记忆。根据提出的能量击穿规则，扩大了样表的吸引域。在此基础上，应用该混沌神经网络对异步电机转子断条故障进行诊断。结果表明，该种方法有助于故障模式的记忆和重现。     

Multilayer associative neural networks (MANN''s): storage capacityversus perfect recall

The objective of this paper is to to resolve important issues in artificial neural nets-exact recall and capacity in multilayer associative memories. These problems have imposed restrictions on coding strategies. We propose the following triple-layered hybrid neural network: the first synapse is a one-shot associative memory using the modified Kohonen's adaptive learning algorithm with arbitrary input patterns; the second one is Kosko's bidirectional associative memory consisting of orthogonal input/output basis vectors such as Walsh series satisfying the strict continuity condition; and finally, the third one is a simple one-shot associative memory with arbitrary output images. A mathematical framework based on the relationship between energy local minima (capacity of the neural net) and noise-free recall is established. The robust capacity conditions of this multilayer associative neural network that lead to forming the local minima of the energy function at the exact training pairs are derived. The chosen strategy not only maximizes the total number of stored images but also completely relaxes any code-dependent conditions of the learning pairs.     

A GCM neural network using cubic logistic map for information processing

A new chaotic neural network described by a modified globally coupled map (GCM) model with cubic logistic map is proposed, which is called CL-GCM model. Its rich dynamical behaviors over a wide range of parameters and the dynamics mechanism of neurons are demonstrated in detail. Furthermore, the network with delay coupling can be precisely controlled to any specified-periodic orbit by feedback control or modulated parameter control with variable threshold. The results of simulations and experiments suggest that the network is controlled successfully. The controlled CL-GCM model exhibits excellent associative memory performance which appears it can output unique fixed pattern or periodic patterns with specified period which contain the stored pattern closest to the initial pattern.

     

Scene analysis by integrating primitive segmentation andassociative memory

Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage with a model of associative memory. The model is a multistage system that consists of an initial primitive segmentation stage, a multimodule associative memory, and a short-term memory (STM) layer. Primitive segmentation is performed by a locally excitatory globally inhibitory oscillator network (LEGION), which segments the input scene into multiple parts that correspond to groups of synchronous oscillations. Each segment triggers memory recall and multiple recalled patterns then interact with one another in the STM layer. The STM layer projects to the LEGION network, giving rise to memory-based grouping and segmentation. The system achieves scene analysis entirely in phase space, which provides a unifying mechanism for both bottom-up analysis and top-down analysis. The model is evaluated with a systematic set of three-dimensional (3-D) line drawing objects, which are arranged in an arbitrary fashion to compose input scenes that allow object occlusion. Memory-based organization is responsible for a significant improvement in performance. A number of issues are discussed, including input-anchored alignment, top-down organization, and the role of STM in producing context sensitivity of memory recall.     

混沌神经网络在分离叠加模式和多对多联想记忆中的应用

混沌是不含外加随机因素的完全确定性的系统表现出来的界于规则和随机之间的内秉随机行为。脑神经系统是由神经细胞组成的网络。类似于人脑思维的人工神经网络与冯·诺依曼计算机相比,在信息处理方面有很大的优越性。混沌和神经网络相互融合的研究是从90年代开始的,其主要的目标是通过分析大脑的混沌现象,建立含有混沌动力学的神经网络模型(即混沌神经网络模型),将混沌的遍历性、对初始值敏感等特点与神经网络的非线性、自适应、并行处理优势相结合,     

一种基于耦合映像格子的彩色图像加密算法

为了改进彩色图像加密算法的安全性等性能,设计了一种基于耦合映像格子的彩色图像加密算法。首先通过一维鲁棒混沌映射对彩色图像的三个基色矩阵基于比特运算完成预处理的置乱操作并分块,对子矩阵进行轮加密,通过耦合映像格子生成S盒,每一轮加密过程先根据辅助密钥选择S盒进行非线性替换,替换后矩阵再两两组合进行双向加密,实现在分量内扩散加密的同时降低相同像素对应三基色分量的相关性。算法将Logistic映射结合明文信息得到混沌系统的初值,有效提高了加密算法对系统初值和明文的敏感性,理论分析及实验表明该算法具有更好的安全性和加密效果。     

An autoassociative neural network model of paired-associate learning

Hebbian heteroassociative learning is inherently asymmetric. Storing a forward association, from item A to item B, enables recall of B (given A), but does not permit recall of A (given B). Recurrent networks can solve this problem by associating A to B and B back to A. In these recurrent networks, the forward and backward associations can be differentially weighted to account for asymmetries in recall performance. In the special case of equal strength forward and backward weights, these recurrent networks can be modeled as a single autoassociative network where A and B are two parts of a single, stored pattern. We analyze a general, recurrent neural network model of associative memory and examine its ability to fit a rich set of experimental data on human associative learning. The model fits the data significantly better when the forward and backward storage strengths are highly correlated than when they are less correlated. This network-based analysis of associative learning supports the view that associations between symbolic elements are better conceptualized as a blending of two ideas into a single unit than as separately modifiable forward and backward associations linking representations in memory.     

Dynamics of selective recall in an associative memory model with one-to-many associations.

The dynamics of selective recall in an associative memory model are analyzed in the scenario of one-to-many association. The present model, which can deal with one-to-many association, consists of a heteroassociative network and an autoassociative network. In the heteroassociative network, a mixture of associative items in one-to-many association is recalled by a key item. In the autoassociative network, the selective recall of one of the associative items is examined by providing a seed of a target item either to the heteroassociative network (Model 1) or to the autoassociative network (Model 2). We show that the critical similarity of Model 2 is not sensitive to the change in the dimension ratio of key vectors to associative vectors, and it has smaller critical similarity than Model 1 for a large initial overlap. On the other hand, we show that Model 1 has smaller critical similarity for a small initial overlap. We also show that unreachable equilibrium states exist in the proposed model.     

Functional-link net computing: theory, system architecture, andfunctionalities

A system architecture and a network computational approach compatible with the goal of devising a general-purpose artificial neural network computer are described. The functionalities of supervised learning and optimization are illustrated, and cluster analysis and associative recall are briefly mentioned     

形态学联想记忆的记忆性能研究

形态学联想记忆在异联想时,在对多个模式对进行记忆之后,逐一对每一个模式对的输入模式进行联想,存在得不到正确的输出模式的情形。对形态学联想记忆在异联想时存在的问题进行研究显得非常的必要,否则,对形态学联想记忆的改进工作就会变得盲目。分析形态学联想记忆的记忆性能,得到几个有意义的结论,通过字符图像的仿真实验,对这些结论进行了验证。     

Competition and cooperation in neuronal processing

A new type of model neuron is introduced as a building block of an associative memory. The neuron, which has a number of receptor zones, processes both the amplitude and the frequency of input signals, associating a small number of features encoded by those signals. Using this two-parameter input in our model compared to the one-dimensional inputs of conventional model neurons (e.g., the McCulloch Pitts neuron) offers an increased memory capacity. In our model, there is a competition among inputs in each zone with a subsequent cooperation of the winners to specify the output. The associative memory consists of a network of such neurons. A state-space model is used to define the neurodynamics. We explore properties of the neuron and the network and demonstrate its favorable capacity and recall capabilities. Finally, the network is used in an application designed to find trademarks that sound alike.     

Two coding strategies for bidirectional associative memory

Enhancements of the encoding strategy of a discrete bidirectional associative memory (BAM) reported by B. Kosko (1987) are presented. There are two major concepts in this work: multiple training, which can be guaranteed to achieve recall of a single trained pair under suitable initial conditions of data, and dummy augmentation, which can be guaranteed to achieve recall of all trained pairs if attaching dummy data to the training pairs is allowable. In representative computer simulations, multiple training has been shown to lead to an improvement over the original Kosko strategy for recall of multiple pairs as well. A sufficient condition for a correlation matrix to make the energies of the training pairs be local minima is discussed. The use of multiple training and dummy augmentation concepts are illustrated, and theorems underlying the results are presented.     

基于级联卷积神经网络的复杂花色布匹瑕疵检测算法

当布匹的背景信息复杂多变时,复杂花色布匹的瑕疵定位与分类较为困难.针对这一问题,文中提出基于级联卷积神经网络的复杂花色布匹瑕疵检测算法.首先,使用双路残差的骨干特征提取网络,在缺陷图和模板图上提取并融合特征.然后,设计密度聚类边框生产器,指导框架中区域候选网络的预检测框设计.最后,通过级联回归方法完成瑕疵的精确定位和分类.采用工业现场采集的布匹图像数据进行训练与预测,结果表明,文中算法的精准率和召回率较高.     

Robust image association by recurrent neural subnetworks

A neural network consisting of a gallery of independent subnetworks is developed for associative memory which stores and recalls gray scale images. Each original image is encoded by a unique stable state of one of neural recurrent subnetworks. Comparing to Amari-Hopfield associative memory, our solution has no spurious states, is less sensitive to noise, and its network complexity is significantly lower. Computer simulations confirm that associative recall in this system for images of natural scenes is very robust. Colored additive and multiplicative noise with standard deviation up to =2 can be removed perfectly from normalized image. The same observations are valid for spiky noise distributed on up to 70% of image area. Even if we remove up to 95% pixels from the original image in deterministic or random way, still the network performs the correct association.     

基于音素混淆网络的蒙古语语音关键词检测方法的研究

蒙古语语音识别系统的词表很难覆盖所有的蒙古文单词,并且随着社会的发展,蒙古文的新词和外来词也越来越多。为了解决蒙古语语音关键词检测系统中的集外词检测问题,该文提出了基于音素混淆网络的蒙古语语音关键词检测方法,并采用音素混淆矩阵改进了关键词的置信度计算方法。实验结果表明,基于音素混淆网络的蒙古语语音关键词检测方法可以较好地解决集外词的检测问题。蒙古语语音关键词检测系统采用改进的置信度计算方法后精确率提高了6%,召回率提高了2.69%,性能得到明显的提升。     

DS-YOLO网络在遥感图像中的飞机检测算法研究

为了解决传统特征提取方法在遥感图像中飞机检测准确率和实时性不足的问题,基于YOLOv3-tiny网络在准确率提升方面提出两点改进。改进点一：将网络提取图像特征点的方式改进为分组卷积,即将一幅图像分成三个通道进行卷积操作,配合通道特征变换以加强各通道之间的语义关联;改进点二：将网络深层特征增加一个尺度检测,并进行上采样与浅层特征图进行融合预测。在速度提升方面引入深度可分离卷积代替传统卷积以降低参数计算量,达到模型轻量化。根据改进后的网络提出一种包含33个卷积层的改进型卷积神经网络DS-YOLO,对改进前后网络分别在自制遥感飞机图像上进行训练,选出最优的权重,用来对目标小、曝光度高、背景干扰等低质量测试集进行测试分析。实验结果表明,改进后的算法在测试集上精准度提升了14.1%,召回率提升了16.8%,检测低质量遥感飞机图像效果更佳。     

Automatic Setting of Article Format Through Neural Networks

The automatic format-setting of journal articles for reducing the workload of computer users involves two processes: automatic acquisition of article format and automatic recall of article formal. Several neural networks have been explored to implement the two processes. The advantages and disadvantages of these neural networks are evaluated in comparison with capabilities of conventional computer programs. A heteroassociative back-propagation network has been developed for the automatic acquisition process. This network excels over computer programs because of its abilities in learning and generalizing implicit knowledge from examples. A bidirectional associative memory network, a Boltzman network, and an autoassociative back-propagation network have been investigated for the automatic recall process. None of them excel over computer programs in terms of recall accuracy.     

Cross-lingual thesaurus for multilingual knowledge management

The Web is a universal repository of human knowledge and culture which has allowed unprecedented sharing of ideas and information in a scale never seen before. It can also be considered as a universal digital library interconnecting digital libraries in multiple domains and languages. Beside the advance of information technology, the global economy has also accelerated the development of inter-organizational information systems. Managing knowledge obtained in multilingual information systems from multiple geographical regions is an essential component in the contemporary inter-organization information systems. An organization cannot claim itself to be a global organization unless it is capable to overcome the cultural and language barriers in their knowledge management. Cross-lingual semantic interoperability is a challenge in multilingual knowledge management systems. Dictionary is a tool that is widely utilized in commercial systems to cross the language barrier. However, terms available in dictionary are always limited. As language is evolving, there are new words being created from time to time. For examples, there are new technical terms and name entities such as RFID and Baidu. To solve the problem of cross-lingual semantic interoperability, an associative constraint network approach is investigated to construct an automatic cross-lingual thesaurus. In this work, we have investigated the backmarking algorithm and the forward evaluation algorithm to resolve the constraint satisfaction problem represented by the associative constraint network. Experiments have been conducted and show that the forward evaluation algorithm outperforms the backmarking one in terms of precision and recall but the backmarking algorithm is more efficient than the forward evaluation algorithm. We have also benchmarked with our earlier technique, Hopfield network, and showed that the associate constraint network (either backmarking or forward evaluation) outperforms in precision, recall, and efficiency.     

New delay-dependent exponential stability criteria of BAM neural networks with time delays

In this paper, the global exponential stability is investigated for the bi-directional associative memory networks with time delays. Several new sufficient conditions are presented to ensure global exponential stability of delayed bi-directional associative memory neural networks based on the Lyapunov functional method as well as linear matrix inequality technique. To the best of our knowledge, few reports about such “linearization” approach to exponential stability analysis for delayed neural network models have been presented in literature. The method, called parameterized first-order model transformation, is used to transform neural networks. The obtained conditions show to be less conservative and restrictive than that reported in the literature. Two numerical simulations are also given to illustrate the efficiency of our result.