An analysis of high-capacity discrete exponential BAM

An exponential bidirectional associative memory (eBAM) using an exponential encoding scheme is discussed. It has a higher capacity for pattern pair storage than conventional BAMs. A new energy function is defined. The associative memory takes advantage of the exponential nonlinearity in the evolution equations such that the signal-to-noise ratio (SNR) is significantly increased. The energy of the eBAM decreases as the recall process proceeds, ensuring the stability of the system. The increase of SNR consequently enhances the capacity of the BAM. The capacity of the exponential BAM is estimated.     

Capacity analysis of the asymptotically stable multi-valuedexponential bidirectional associative memory

The exponential bidirectional associative memory (eBAM) has been proposed and proved to be a stable and high capacity associative neural network. However, the intrinsic structure and the evolution functions of this network restrict the representation of patterns to be either bipolar or binary vectors. We consider the promising development of multi-valued systems and then design a multi-valued discrete eBAM (MV-eBAM). The multi-valued eBAM has been proved to be asymptotically stable under certain constraints. Although MV-eBAM is also verified to possess high capacity by thorough simulations, there are important characteristics to be explored, including the absolute lower bound of the radix, and the approximate capacity. In order to estimate the capacity of the MV-eBAM, a modified evolution equation is also proposed. Hence, an analytic solution is derived. Besides, a radix searching algorithm is presented such that the absolute lower bound of the radix for this MV-eBAM can be found.     

The majority theorem of centralized multiple BAMs networks

A method for modeling the learning of belief combination in evidential reasoning using a neural network is presented. A centralized network composed of multiple bidirectional associative memories (BAMs) sharing a single output array of neurons is proposed to process the uncertainty management of many pieces of evidence simultaneously. The convergence properties of the multi-BAM network are proved. The combination process of evidence is considered as a resonant process through the multi-BAM networks. Most important of all, a majority rule of decision making in presentation of multiple evidence is also found by the study of signal-noise-ratio (SNR) of the multi-BAM network. Some simulation examples are given. The result is coherent with the intuition of reasoning.     

多重加权多值指数双向联想记忆网络及其表决性能

Wang和陈等利用各自提出的二值指数双向联想记忆模型（eBAM)及其改进型eBAM(IeBAM),分别构造了由多个eBAM和IeBAM组成的多重eBAM(Multi-eBAM)和多重IeBAM(Multi-IeBAM)的信念组合模型,使之可模拟多个专家的表决。该文在此基础上,借助陈提出的多值eBAM(MVeBAM),提出了多重多值eBAM (Multi-MVeBAM),对Multi-eBAM和Multi-IeBAM进行了两方面的推广;一是将二值表示推广到多值表示,以此可以处理现实中的多值数据;二是将原有模型中具有同等权威度的各专家推广到各具不同的权威度的专家,以此模拟更实际的表决情形。文中借助能量函数证明了所提模型的渐近稳定性,以保证其实际可用。计算机模拟证实了模型的可行性。     

多重改进型指数双向联想记忆模型及其在多证据推理中的决策性能

提出了多证据推理中采用神经网络来模拟信念组合学习方法。网络由多个改进型指数双向联想记忆模型（IeBAM）构成,并且共享一个输出来同时进行多证据不确定性的管理。文中证明了多重IeBAM(Multi-IeBAM）的稳定性,讨论了在多条证据同时提交网络后的多数规则。理论和实验都证明了多数因子比Wang所提模型更紧凑、更严格,从而可保证在受一定程度的干扰下,专家们仍能做出正确决策。最后所给出的模拟例子的结果与直觉推理相吻合。     

Recall and Reasoning—an information theoretical model of cognitive processes

Cognitive Psychology studies humans’ capabilities to memorize and recall knowledge and images, among others. Connectionistic, propositional and conceptual models are a means to survey these phenomenons. This paper proposes an information theoretical network for simulating stimulus and response in categorical structures. A stimulus triggers an information flow throughout the whole network and generates for all ideas representing vertices an impact in the information theoretical unit [bit], thus measuring the recall intensity and producing a response. The method is shown to yield results of high performance even for complex taxonomies and connectionistic models. Reasoning is the logical counterpart of recall. Once an idea is associated with a stimulus, logical dependencies between both must be established, if required. Information theoretical networks allow to switch between a recall mode and a reasoning mode, also permitting logical reasoning within the same framework. Both capabilities are demonstrated by suitable examples.     

Data compression by the recursive algorithm of exponentialbidirectional associative memory

A novel data compression algorithm utilizing the histogram and the high-capacity exponential bidirectional associative memory (eBAM) is presented. Since eBAM has been proved to possess high capacity and fault tolerance, it is suitable to be utilized in the data compression using the table-lookup scheme. The histogram approach is employed to extract the feature vectors in the given data. The result of the simulation of the proposed algorithm turns out to be better than the traditional methods.     

A deterministic capacity-finding method for multi-valuedexponential BAM

The multi-valued exponential bidirectional associative memory (MV-eBAM) has been proposed and proved to be asymptotically stable under certain constraints. Although multi-valued eBAM has been verified to possess high capacity by thorough simulations, the capacity is still unable to be solved analytically. In the paper, an algorithm is proposed to derive the capacity. Some important characteristics, including the absolute lower bound of the radix, and the approximate capacity are also discussed. The result shows that the multi-valued eBAM indeed possesses high capacity     

改进的指数双向联想记忆模型在数据压缩中的应用

改进的指数双向联想记忆模型（Ｉmproved exponential bidirectional associative memory molel,IeBAM)是在eBAM的基础上通过引入内连接项而产生的一个比eBAM具有更高存储容量,纠错性的联想神网络,借助于ＩeBAM的高存储容量和良好的纠错性能及有序直方,要实现一种更高效率的数据压缩方法,从而为现有的数据压缩方法提供一种新算法,最后,计算机模拟证实了使用ＩeBAM的数据压缩性能比使用eBAM的更好。     

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.     

Disjoint path properties of the data manipulator network family

A critical component of any parallel processing system is the interconnection network that provides communications among the system's processors and memories. The data manipulator (gamma) network family is an important class of multistage interconnection networks that is being studied by various researchers. One interesting property of the data manipulator network family is the existence of multiple paths through the network for most source/ destination pairs. The condition that must be present to have disjoint paths through the network for a given source/ destination pair is shown, where disjoint paths are multiple paths with no links in common. It is derived that the maximum number of disjoint paths for any source/destination pair is two and a method for finding the routing tags that specify these paths is given. For source/destination pairs that have disjoint paths, a single fault cannot prevent communication between that source/ destination pair. The effect of a fault in a given stage of the network on the number of source/destination pairs that can be connected is also discussed. All results are proven mathematically.     

一种新型双向联想记忆神经网络

提出了一种新型双向联想记忆神经网络,此网络将两个相互关联的模式以模式对的形式存储在由N个连接构成的模式环中,记忆容量为22N数量级,完全消除了假模式对、能够全部或部分地回忆出与输入模式对具有最小Hamming距的被记忆的模式对,同时具有较高的记忆效率和可靠性。连接由“连接状态”和“禁止路径”组成,前者直接存储二进制模式对向量的分量,后者用于消除假模式;此神经网络具有正向联想、逆向联想和自联想方式,使得网络能更灵活有效地满足不同的回忆要求。     

基于模糊逻辑和组合证据理论的信息融合技术在网络管理中的应用

研究基于模糊逻辑和组合证据理论的综合信息融合技术在网络管理中的应用．研究了用于网络管理的来源于多信息源的关联规则的融合方法和推理机制，以及故障与故障原因的模糊关系和模糊规则的融合方法及推理机制；在故障定位方面，采用组合证据理论对网络专家、规则推理和模糊推理所给出的故障原因进行融合得出综合的诊断结果。     

A topological and temporal correlator network for spatiotemporalpattern learning, recognition, and recall

In this paper, we describe the design of an artificial neural network for spatiotemporal pattern recognition and recall. This network has a five-layered architecture and operates in two modes: pattern learning and recognition mode, and pattern recall mode. In pattern learning and recognition mode, the network extracts a set of topologically and temporally correlated features from each spatiotemporal input pattern based on a variation of Kohonen's self-organizing maps. These features are then used to classify the input into categories based on the fuzzy ART network. In the pattern recall mode, the network can reconstruct any of the learned categories when the appropriate category node is excited or probed. The network performance was evaluated via computer simulations of time-varying, two-dimensional and three-dimensional data. The results show that the network is capable of both recognition and recall of spatiotemporal data in an online and self-organized fashion. The network can also classify repeated events in the spatiotemporal input and is robust to noise in the input such as distortions in the spatial and temporal content.     

主客观证据融合模型及其应用研究

油田剩余油分布预测被国内外石油领域专家公认为世界难题,目前,其预测准确率低的根源在于或者只考虑部分客观证据、或者只考虑部分主观证据,导致对剩余油分布水淹类型等特征分类准确率低、可靠性差。所以,如何对来自多专业领域不同层次的全部客观证据及领域专家长期积累的主观证据进行融合,成为剩余油分布研究的核心问题。文章通过BP神经网络联合模型与两级D-S证据推理模型的优势互补进行主客观证据融合,实现了剩余油分布多属性特征的准确分类。提出了将BP神经网络分类结果的可信度及专家系统推理结论的可信度作为D-S证据推理模型输入证据基本概率赋值的有效方法。为各类多源信息融合系统的研究和工程实现提供了示例、途径和有益的经验。     

FuzzyShell: a large-scale expert system shell using fuzzy logic foruncertainty reasoning

There exist in the literature today many contributions dealing with the incorporation of fuzzy logic in expert systems. However, unfortunately, much of what has been proposed can only be applied to small-scale expert systems; that is, when the number of rules is in the dozens as opposed to in the hundreds. The more traditional (nonfuzzy) expert systems are able to cope with large numbers of rules by using Rete networks for maintaining matches of all the rules and all the facts. (A Rete network obviates the need to match the rules with the facts on every cycle of the inference engine.) In this paper, we present a more general Rete network that is particularly suitable for reasoning with fuzzy logic. The generalized Rete network consists of a cascade of three networks: the pattern network, the join network, and the evidence aggregation network. The first two layers are modified versions of similar layers for the traditional Rete networks and the last, the aggregation layer, is a new concept that allows fuzzy evidence to be aggregated when fuzzy inferences are made about the same fuzzy variable by different rules     

Connectionist-based Dempster-Shafer evidential reasoning for data fusion

Dempster-Shafer evidence theory (DSET) is a popular paradigm for dealing with uncertainty and imprecision. Its corresponding evidential reasoning framework is theoretically attractive. However, there are outstanding issues that hinder its use in real-life applications. Two prominent issues in this regard are 1) the issue of basic probability assignments (masses) and 2) the issue of dependence among information sources. This paper attempts to deal with these issues by utilizing neural networks in the context of pattern classification application. First, a multilayer perceptron neural network with the mean squared error as a cost function is implemented to calculate, for each information source, posteriori probabilities for all classes. Second, an evidence structure construction scheme is developed for transferring the estimated posteriori probabilities to a set of masses along with the corresponding focal elements, from a Bayesian decision point of view. Third, a network realization of the Dempster-Shafer evidential reasoning is designed and analyzed, and it is further extended to a DSET-based neural network, referred to as DSETNN, to manipulate the evidence structures. In order to tackle the issue of dependence between sources, DSETNN is tuned for optimal performance through a supervised learning process. To demonstrate the effectiveness of the proposed approach, we apply it to three benchmark pattern classification problems. Experiments reveal that the DSETNN outperforms DSET and provide encouraging results in terms of classification accuracy and the speed of learning convergence.     

基于模糊神经网络的飞行仿真转台控制

针对飞行仿真转台系统的非线性问题，提出了基于模糊神经网络的自适应控制方法，并且提出了新的推理算法，该控制方法结合了神经网络和模糊推理的优点，可以更合理地选择初始权值，既可提高神经网络的学习过程又可在线寻优模糊规则，通过实验表明该控制方法可以明显提高控制系统的跟踪性能，并且具有很强的对外干扰和非线性因素的鲁棒性。     

D-S证据理论在决策支持系统中的应用

D-S证据理论提供了一种解决多数据源不确定信息推理和融合的有效方法。证据理论能够对各自独立的证据加以综合给出一致性结果,并能处理具有模糊和不确定信息的合成问题,最终达到信息互补。与其他推理方法相比更符合人类思维决策过程。为此,提出一种基于D-S证据理论的灾害决策支持方法,并根据试验结果验证了该方法的有效性和可行性。