具有内连接的指数多值双向联想记忆模型

C_C Wang的多值指数双向联想记忆模型(MVeBAM)是一种高存储容量的联想神经网络.本文在MVeBAM的基础上通过引入自相关项(或内连接)提出了一个新的具有内连接的多值指数双向联想记忆模型,推广了MVeBAM.通过定义简单的能量函数证明了其在同、异步方式下的稳定性,从而保证了所学模式对成为被推广的MVeBAM(EMVeBAM)的稳定点.最后,计算机模拟证实了EMVeBAM比MVeBAM具有更高的存储容量和更好的纠错性能.     

一个新的高阶双向联想记忆模型及其性能估计

提出了一个新的高阶双向联想记忆模型.它推广了由Tai及Jeng所提出的高阶双向联想记忆模型HOBAM(higher-order bidirectional associative memory)及修正的具有内连接的双向联想记忆模型MIBAM(modified intraconnected bidirectional associative memory),通过定义能量函数,证明了新模型在同步与异步更新方式下的稳定性,从而能够保证所有被训练模式对成为该模型的渐近稳定点.借助统计分析原理,估计了所提模型的存储容量.计算机模拟证实此模型不仅具有较高的存储容量,而且还具有较好的纠错能力.     

内连式复值双向联想记忆模型及性能分析

Lee的复域多值双向联想记忆模型(complex domain bidirectional associative memory,简称CDBAM)不仅将Kosko的实域BAM(bidirectional associative memory)推广至复域,而且推广至多值情形,以利于多值模式(如灰级图像等)间的联想.在此基础上,提出了一个新的推广模型:复域内连式多值双向联想记忆模型(intraconnected CDBAM,简称ICDBAM),通过定义的能量函数证明了它在同步与异步更新方式下的稳定性,从而保证所有训练样本对成为其稳定点,克服了CDBAM所存在的补码问题.计算机模拟证明了该模型比CDBAM具有更高的存储容量和更好的纠错性能.     

推广的多值指数双向联想记忆模型及其应用

推广了Wang的多值指数双向联想记忆(multi-valued exponential bi-directional associative memory,简称MV-eBAM)模型,使其成为所提出的推广的多值指数双向联想记忆 (extended MV-eBAM,简称EMV-eBAM) 模型的一个特例.EMV-eBAM具有比前者更高的存储容量和纠错性能,因此利用这种性能,设计了一种基于联想记忆的新型图像压缩算法.该算法在无噪声情况下具有与矢量量化(vector quantization,简称VQ)算法相近的性能,而在双重(信道和图像)噪声环境下则具有显著的抑制效果.对比实验结果显示,在添加5%椒盐噪声下,该算法几乎能完全排除噪声干扰,而VQ则反而放大了噪声.该算法的另一个优点是,当在差错信道中传送时,可以获得比采用循环纠错码更强的纠错性能.因而,该算法具有较强的鲁棒性.     

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。     

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。     

离散指数型BAM网络的记忆容量

基于Kosko的双向联想记忆模型BAM(bidirectional associative memory)原理,本文提出了一个离散指数型双向联想记忆模型.通过理论分析证实,该模型的记忆容量远远大于BAM的记忆容量.本文给出了指数型BAM记忆容量的下界.     

多值指数式多向联想记忆模型

多向联想记忆MDAM(multidirectional associative memory)模型是Kosko双向联想记忆模型BAM(bidirectional associative memory)的一个直接推广,它可应用于数据融合及维数分裂,使模型能处理大维数输入问题.目前所提出的若干种多向模型均局限于二值输入/输出模式对,但如在图象处理等的实际应用中,所处理的模式均是多值的.本文的目的就是提出一个多值指数式多向联想记忆模型MVeMDAM(multivalued exponential multidi     

一种基于MRⅡ算法的三层二值双向联想记忆网络

传统的两层二值双向联想记忆(BAM)网络因其结构的限制存在着存储容量有限、区分小差别模式和存储非正交模式能力不足的缺陷,结构上将其扩展至三层网络是一个有效的解决思路,但是三层二值BAM网络的学习是一个难题,而三层连续型BAM网络又存在处理二值问题不方便的问题。为了解决这些问题,提出一种三层结构的二值双向联想记忆网络,创新之处是采用了二值多层前向网络的MRⅡ算法实现了三层二值BAM网络的学习。实验结果表明,基于MRⅡ算法的三层二值BAM网络极大地提高了网络的存储容量和模式区分能力,同时保留了二值网络特定的优势,具有较高的理论与实用价值。     

模糊联想记忆网络的增强学习算法

针对 Kosko提出的最大最小模糊联想记忆网络存在的问题 ,通过对这种网络连接权学习规则的改进 ,给出了另一种权重学习规则 ,即把 Kosko的前馈模糊联想记忆模型发展成为模糊双向联想记忆模型 ,并由此给出了模糊快速增强学习算法 ,该算法能存储任意给定的多值训练模式对集 .其中对于存储二值模式对集 ,由于其连接权值取值 0或 1,因而该算法易于硬件电路和光学实现 .实验结果表明 ,模糊快速增强学习算法是行之有效的 .     

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.     

改进的指数双向联想记忆模型及性能估计

提出了一个新的改进型指数双向联想记忆模型(improved eBAM,简称IeBAM).通过定义有界且随状态改变而下降的能量函数,证明了IeBAM在状态的同、异步更新方式下的稳定性,一方面排除了Wang的修正指数BAM(modified eBAM,简称MeBAM)和Jeng的eBAM(exponential BAM)的稳定性证明中所作的不合理假设;另一方面,放宽了对BAM(bidirectional associative memory)的连续性假设的要求,并避免了补码问题.理论分析和计算机模拟结果表明,     

A Bidirectional Hetero-Associative Memory for True-Color Patterns

Classical bidirectional associative memories (BAM) have poor memory storage capacity, are sensitive to noise, are subject to spurious steady states during recall, and can only recall bipolar patterns. In this paper, we introduce a new bidirectional hetero-associative memory model for true-color patterns that uses the associative model with dynamical synapses recently introduced in Vazquez and Sossa (Neural Process Lett, Submitted, 2008). Synapses of the associative memory could be adjusted even after the training phase as a response to an input stimulus. Propositions that guarantee perfect and robust recall of the fundamental set of associations are provided. In addition, we describe the behavior of the proposed associative model under noisy versions of the patterns. At last, we present some experiments aimed to show the accuracy of the proposed model with a benchmark of true-color patterns.     

Recurrent correlation associative memories

A model for a class of high-capacity associative memories is presented. Since they are based on two-layer recurrent neural networks and their operations depend on the correlation measure, these associative memories are called recurrent correlation associative memories (RCAMs). The RCAMs are shown to be asymptotically stable in both synchronous and asynchronous (sequential) update modes as long as their weighting functions are continuous and monotone nondecreasing. In particular, a high-capacity RCAM named the exponential correlation associative memory (ECAM) is proposed. The asymptotic storage capacity of the ECAM scales exponentially with the length of memory patterns, and it meets the ultimate upper bound for the capacity of associative memories. The asymptotic storage capacity of the ECAM with limited dynamic range in its exponentiation nodes is found to be proportional to that dynamic range. Design and fabrication of a 3-mm CMOS ECAM chip is reported. The prototype chip can store 32 24-bit memory patterns, and its speed is higher than one associative recall operation every 3 mus. An application of the ECAM chip to vector quantization is also described.     

Stability and statistical properties of second-order bidirectionalassociative memory

In this paper, a bidirectional associative memory (BAM) model with second-order connections, namely second-order bidirectional associative memory (SOBAM), is first reviewed. The stability and statistical properties of the SOBAM are then examined. We use an example to illustrate that the stability of the SOBAM is not guaranteed. For this result, we cannot use the conventional energy approach to estimate its memory capacity. Thus, we develop the statistical dynamics of the SOBAM. Given that a small number of errors appear in the initial input, the dynamics shows how the number of errors varies during recall. We use the dynamics to estimate the memory capacity, the attraction basin, and the number of errors in the retrieved items. Extension of the results to higher-order bidirectional associative memories is also discussed.