Hopfield连续联想记忆的吸引域和收敛速度研究

本文利用某些技巧和Ｌｙａｐｕｎｏｖ方法,得到了Ｈｏｐｆｉｅｌｄ连续联想记忆模式的吸收域及其中每一点趋向记忆模式的指数收敛速度的一些全新的估计结果。这些结果可用于评价Ｈｏｐｆｉｅｌｄ连续反馈联想记忆网络的容错能力,且可用于综合连续反馈联想记忆网络。     

Hopfield联想记忆编码方法的加速和优化

本文提出了一种Ｈｏｐｆｉｅｌｄ自联想记忆的编码方法：首先对每一记忆模式，将联想记忆的编码问题看出作感知机的学习问题，结合感知机学习规则和投影映射加速学习；其次根据联想记忆对网络权值矩阵的限制所构成的集Ｓ为凸集，将经过学习所得的矩阵投影到集Ｓ上；最后对所有记忆模式交替地进行前面的学习过程。     

连续双向联想记忆模型的稳定性分析

对于连续型Ｈｏｐｆｉｅｌｄ模型的平衡态特征，目前人们已经得到了很多富有意义的成果，本文说明，连续Ｈｏｐｆｉｅｌｄ模型的大部分结论都可以推广到连续双向联想记忆模型，我们重点讨论了平衡态条件、渐近稳定性以及围绕一稳定平衡点的吸引域等问题，所得到的结论对于ＢＡＭ的设计和应用都是很有意义的。     

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。     

二进Hopfield型神经网络的记忆容量

本文证明了具有Ｎ个神经元的二进Ｈｏｐｆｉｅｌｄ型神经网络可存储的记忆模式的最大数目为２＾Ｎ，对于任意Ｋ（１≤Ｋ≤２＾Ｎ）个Ｎ维二进值向量，给出了它们成为具有Ｎ个神经元的二进Ｈｏｐｆｉｅｌｄ型神经网络稳定态的充要条件。文中指出了一个二进Ｈｏｐｆｉｅｌｄ型神经网络有可能没有任何稳定态，这是与连续Ｈｏｐｆｉｅｌｄ型神经网络的一个重要区别。最后，给出本文的主要结论。     

Hopfield连续联想记忆的吸引域和收敛速度研究

本文利用某些技巧和Lyapunov方法,得到了Hopfield连续联想记忆模式的吸引域及其中每一点趋向记忆模式的指数收敛速度的一些全新的估计结果。这些结果可用于评价Hopfield连续反馈联想记忆网络的容错能力,且可用于综合连续反馈联想记忆网络。     

离散Hopfield神经网络和联想记忆的开关电流技术实现

研究了离散Ｈｏｐｆｉｅｌｄ神经网络（ＤＨＮＮ）和联想记忆神经网络的开关电流技术实现，利用多权输入跨导，开关电流延迟器（ＳＩＤ）和可编程电流比较器（ＰＣＣ）实现了离散Ｈｏｐｉｅｌｄ神经网络，并提出了利用离散Ｈｏｐｆｉｅｌｄ神经网络实现自联想记忆时相应的开关电流电路，所提出了开关电流神经网络适宜于超大规模集成，能在低电压（如３．３Ｖ）下工作。     

适合于数字VLSI实现的指数相关联想记忆等效运算算法

适合于数字ＶＬＳＩ实现的指数相关联想记忆等效运算算法杨绿溪，王保云，何振亚（东南大学无线电工程系，南京２１００１８）自１９８２年Ｈｏｐｆｉｅｌｄ网络被用于联想记忆，人们一直在致力于研究新的高容量联想记忆神经网络，Ｒ．Ｍ．Ｇｏｏｄｍａｎ等人提出的指数相...     

连续反馈联想记忆的吸引域和指数收敛速度的估计及其应用

估计了连续反馈联想记忆模式的吸引域及其中每一点趋向记忆模式的指数收敛速度。这些结果可用于连续反馈联想记忆网络的容错性能评价以及综合过程。     

连续反馈联想记忆的吸引域和指数收敛速度的估计及其应用

估计了连续反馈联想记忆模式的吸引域及其中每一点趋向记忆模式的指数收敛速度。这些结果可用于连续反馈联想记忆网络的容错性能评价以及综合过程。     

ESTIMATION OF ATTRACTION DOMAIN AND EXPONENTIAL CONVERGENCE RATE OF CONTINUOUS FEEDBACK ASSOCIATIVE MEMORY AND ITS APPLICATIONS

The attraction domains of memory patterns and exponential convergence rate of the network trajectories to memory patterns for continuous feedback associative memory are estimated. These results can be used for evaluation of error-correction capability and the synthesis procedures for continuous-time associative memory neural networks.     

综合联想记忆神经网络的外积取等准则

本文提出了一个新的联想记忆设计准则，即外积取等准则，它具有外积和准则的所有优点。由外积取等准则设计出的联想记忆网络能够存储任意给定的训练模式，即对于训练模式的数目和它们之间相关性的强弱没有限制。外积取等准则可用来定量地评价记忆模式向量各分量对于记忆模式分类或识别的重要性。由外积取等准则设计出的网络的连接权值只取１、０或－１，因而网络易于光学实现。计算机实验结果充分说明了外积取等准则的有效性。     

The classification and associative memory capability of stackfilters

The notion of the on-set of a positive Boolean function is used to classify stack filters into three different types, called decreasing, increasing, and mixed. The associative memory capability of each of these three types of stack filters is then investigated. The associative memory of a stack filter is defined to be the set of root signals of that filter. In a class of stack filters in which each filter's root set contains a desired set of patterns, those filters whose root sets have the smallest cardinality are said to be minimal among all filters in that class for that set of patterns. Some learning schemes are proposed to find minimal decreasing and increasing stack filters. It is also shown that, for any specified set of patterns, there is always a mixed stack filter which is minimal when one considers all stack filters which preserve those patterns. In this sense, mixed stack filters are always at least as good as decreasing or increasing stack filters     

Time discretization of continuous-time filters and smoothers forHMM parameter estimation

In this paper we propose algorithms for parameter estimation of fast-sampled homogeneous Markov chains observed in white Gaussian noise. Our algorithms are obtained by the robust discretization of stochastic differential equations involved in the estimation of continuous-time hidden Markov models (HMM's) via the EM algorithm. We present two algorithms: the first is based on the robust discretization of continuous-time filters that were recently obtained by Elliott to estimate quantities used in the EM algorithm; the second is based on the discretization of continuous-time smoothers, yielding essentially the well-known Baum-Welch re-estimation equations. The smoothing formulas for continuous-time HMM's are new, and their derivation involves two-sided stochastic integrals. The choice of discretization results in equations which are identical to those obtained by deriving the results directly in discrete time. The filter-based EM algorithm has negligible memory requirements; indeed, independent of the number of observations. In comparison the smoother-based discrete-time EM algorithm requires the use of the forward-backward algorithm, which is a fixed-interval smoothing algorithm and has memory requirements proportional to the number of observations. On the other hand, the computational complexity of the filter-based EM algorithm is greater than that of the smoother-based scheme. However, the filters may be suitable for parallel implementation. Using computer simulations we compare the smoother-based and filter-based EM algorithms for HMM estimation. We provide also estimates for the discretization error     

时空混沌控制在联想记忆中的应用

本文提出了一种具有时空混沌控制的联想记忆网络.实验结果表明:具有目标信息的一部分知识的初始输入能在时空混沌的参数控制中成功地完成联想记忆,根据提出的学习算法,该网络的记忆搜索性能和记忆容量比Hopfield模型有较大改善.同时发现联想记忆成功率与强化因子、样本数、信息率、学习阈值以及初始混沌参数有关.     

Architectural design and analysis of learnable self-feedback ratio-memory cellular nonlinear network (SRMCNN) for nanoelectronic systems

In this paper, a learnable cellular nonlinear network (CNN) with space-variant templates, ratio memory (RM), and modified Hebbian learning algorithm is proposed and analyzed. By integrating both the modified Hebbian learning algorithm with the self-feedback function and a ratio memory into CNN architecture, the resultant ratio-memory (RMCNN) is called the self-feedback RMCNN (SRMCNN) which can serve as the associative memory. It can generate the absolute weights and then transform them into the ratioed A-template weights as the ratio memories for recognizing noisy input patterns. Simulation results have shown that with the stronger feature enhancement effect, the SRMCNN under constant leakage current can store and recognize more patterns than the RMCNN. For 18 /spl times/ 18 SRMCNN, 93 noisy patterns with a uniform distribution noise level of 0.8 and a variance of normal distribution noise of 0.3 can be learned, stored, and recognized with 100% success rate. The SRMCNN has greater learning and recognition capability when the learned patterns are simpler and the noise is lower. For the learning and recognition of complicated patterns, the allowable pattern number is decreased for a 100% success rate. Simulation results have successfully verified the correct functions and better performance of SRMCNN in the pattern recognition. With high integration capability and excellent pattern association performance, the proposed SRMCNN can be applied to nanoelectronic associative-memory systems for image processing applications.     

双向联想记忆神经网络的开关电流技术实现

本文研究了双向联想记忆（ＢＡＭ）神经网络的开关电流技术实现，提出了实现负权值及存储联想矢量的两个开关电流单元电路，基于此，给出了双向联想记忆网络的开关电流电路，文中对三神经元双向联想记忆ＳＩ网络进行了ＰＳＰＩＣＥ仿真，结果表明所提出的ＳＩ联想记忆网络是正确的。     

光学图像模糊关联存贮器

本文提出一种二维图像模糊关联存贮器的光学实现方法。通过面积编码模糊矩阵，在多重成像系统下实现了模糊关联存贮器所需的最大一最小合成运算。给出了实验结果。