双向联想记忆学习与回忆的研究

本文对双向联想记忆(BAM)的学习与回忆过程进行了详细的分析。在学习过程中,先是运用自适应非对称BAM算法进行学习,进而采用设置印象门限的反复记忆算法进行学习,本文从理论上证明了印象门限与样本吸引域之间的关系,指出反复记忆方法的理论依据。回忆过程中,采用非零阈值函数的运行方程,提出了阈值学习方法,并且从理论上证明了非零阈值函数的运行方程的采用,可进一步扩大吸引域。为了进一步扩大网络的信息存储量,本文引入了并联的BAM结构。本文方法的采纳,使得BAM网络的信息存储量、误差校正能力等得到很大程度的提高。     

对数-指数形态学联想记忆

利用对数和指数算子构建了一种新的形态学联想记忆方法,简称LEMAM.理论分析表明:自联想LEMAM(简称ALEMAM)具有无限存储能力、一步回忆记忆、一定的抵抗腐蚀噪声或膨胀噪声的能力,在输入完全或在一定的噪声范围内,能够保证完全回忆记忆;异联想LEMAM(简称HLEMAM)在输入完全情况下,不能保证完全回忆记忆,但当满足一定条件时,也能够达到完美联想记忆.对比实验结果表明:在一些情况下,LEMAM能够取得较好的联想记忆效果.总体来说,LEMAM丰富了形态学联想记忆的理论和实践,可以作为一种神经计算模型加以研究和利用.     

联想记忆与人工神经网络

联想记忆是人类记忆的基本方式,本文通过对人类联想记忆的本质及其规律的分析,讨论了如何用人工神经网络的模型来实现这种记忆形式,同时也指出了这种模拟的不足之处及需要解决的问题。     

基于小世界体系的投影学习联想记忆模型研究

联想记忆是神经网络的重要应用之一,传统Hopfield网络所用的外积法限制了输入向量的模式,降低了网络的联想性能,而且全瓦连的结构增加了网络的复杂性,不符合神经生物学观点.针对这些问题.提出一种新型的小世界联想记忆模型,用局部的规则连接和稀疏的长程连接取代全互连结构,降低网络的复杂性,同时引入投影学习规则来提高网络的回忆能力和抗噪能力.通过matlab软件对该模型模拟仿真,并与其他模型进行比较,结果表明,该模型在有效降低网络复杂度的情况下,保持了良好的同忆件能.     

基于小世界体系的指数自联想记忆模型研究

全互连结构是大多数神经联想记忆模型采用的连接方式．然而,无论从神经生物学的观点还是从硬件实现角度出发,在确保局部连接占主体地位的情况下,最小化神经元间的连接长度是合乎逻辑的．由Watts和Strogatz提出的小世界体系（SWA）为解决这一问题提供了一条有趣途径．借鉴这一具有一定神经生物学特点的小世界体系,构建出一个基于小世界体系的指数自联想记忆模型（SWEAM）,其在结构上更接近人脑的生物学特性,同时在存储容量和抗噪声性能上优于现有的同类联想记忆模型．因采用了SWA,SWEAM在工艺实现上也更容易．     

对基于匹配滤波器的联想记忆模型的分析

近来,一些学者提出了用匹配滤波器实现的联想记忆模型,本文对这种模型进行了详细的分析。首先,讨论了模型中记忆样本模式的稳定性,提出了几个保证稳定性的充分条件;其次,分析了模型的误差校正能力,指出了当要求样本模式具有一定的吸引性时,模型中非线性加权函数应满足的约束条件;最后,利用信噪比分析了模型的记忆容量,并指出在取加权函效为指数函数的情况下,记忆容量与样本矢量的长度N成指数关系。     

基于αβ运算的多层联想记忆模型的研究

介绍了αβ运算符的定义和αβ联想记忆矩阵的四种操作。通过四种矩阵操作来实现模式对的培训和回忆。αβ多层联想记忆模型相比形态学联想记忆模型数值计算相对容易。最后,通过αβ多层联想记忆的数字模拟实例验证了αβ多层联想记忆具有良好的回忆性能。     

一种基于稀疏分布记忆模型的汉字联想记忆方法

本文描述了Ｋａｎｅｒｖａ的稀疏分布记忆模型，指出了它在用于汉字联想时的问题，同时提出了改进的模型，试验表明，这种改进模型使记忆容量和容错能力大大提高。     

Handwritten digit recognition by means of a holographic associative memory

In this paper, a holographic associative memory (HAM) is proposed for recognizing handwritten variations of the ten digits. First, the handwritten characters were taken from the NIST standard database in order to extract relevant features from each one of them. Each digit was thus represented as a vector of 112 features constructed by dividing each character into 16 equal-sized partitions, each one used to extract seven different features for recognition. Second, these feature vectors, and reduced combinations of them, were input to train several HAM systems respectively. Then, all these memories were tested with a new set of patterns and the lowest-error HAM was chosen as the best training set. The features used in this last memory were taken as the most significant variables for describing each digit in the database. Finally, these most significant features were used to show the behaviour of the recognition rate when training the HAM with reduced training sets. Some final conclusions are reported and future work directions are proposed.     

Associative Memory Design via Path Embedding into a Graph

A graph theoretical procedure for storing a set of n-dimensional binary vectors as asymptotically stable equilibrium points of a discrete Hopfield neural network is presented. The method gives an auto-associative memory which stores an arbitrary memory set completely. Spurious memories might occur only in a small neighborhood of the original memory vectors, so cause small errors.     

形态学联想记忆的研究综述*

通过提炼出来的一个形态学联想记忆的研究框架,可以很清晰地概括出形态学联想记忆的研究成果,从而可以很合理地归纳出形态学联想记忆仍存在的问题以及今后的发展方向。此形态学联想记忆的研究框架对形态学联想记忆的进一步研究具有一定的指导意义。     

A Web-based collaborative filtering system

In this paper we describe a collaborative filtering system for automatically recommending high-quality information to users with similar interests on arbitrarily narrow information domains. It asks a user to rate a gauge set of items. It then evaluates the user's rates and suggests a recommendation set of items. We interpret the process of evaluation as an inference mechanism that maps a gauge set to a recommendation set. We accomplish the mapping with fuzzy associative memory. We implemented the suggested system in a Web server and tested its performance in the domain of retrieval of technical papers, especially in the field of information technologies. The experimental results show that it may provide reliable recommendations.     

Neural associative memory for brain modeling and information retrieval

This work concisely reviews and unifies the analysis of different variants of neural associative networks consisting of binary neurons and synapses (Willshaw model). We compute storage capacity, fault tolerance, and retrieval efficiency and point out problems of the classical Willshaw model such as limited fault tolerance and restriction to logarithmically sparse random patterns. Then we suggest possible solutions employing spiking neurons, compression of the memory structures, and additional cell layers. Finally, we discuss from a technical perspective whether distributed neural associative memories have any practical advantage over localized storage, e.g., in compressed look-up tables.     

Further Results on the Asymptotic Memory Capacity of the Generalized Hopfield Network

This paper presents a further theoretical analysis on the asymptotic memory capacity of the generalized Hopfield network (GHN) under the perceptron learning scheme. It has been proved that the asymptotic memory capacity of the GHN is exactly 2(n– 1), where n is the number of neurons in the network. That is, the GHN of n neurons can store 2(n– 1) bipolar sample patterns as its stable states when n is large, which has significantly improved the existing results on the asymptotic memory capacity of the GHN.     

最小平方形态联想记忆模型的研究与实现

Ritter等人借助形态学理论提出了形态联想记忆模型（MAM Morphological Associatvie Memory)，其中所构建模型的两个权值矩阵和可分别用以回忆腐蚀和膨胀噪声模式，但不能回忆混合噪声模式，故本文提出了一个最小平方形态联想记忆模式（LSMAM least squares MAM)来克服MAM的不足，以达到既可分别识别腐蚀和膨胀噪声模式，也可以识别混合型噪声模式的目的，因此更适用于实际情形，实验结果表明了该方法的可行性。     

GAM模型稳定性分析及其在图像识别中的应用

多值指数关联联想记忆模型（MMECAM）是一种高存储容量的自联想记忆神经网络。在详细分析其优缺点的基础上,通过改进MMECAM模型的更新规则,首先提出一个新的高斯自联想记忆模型（GAM）,然后通过定义简单的能量函数从理论上证明其在同、异步方式下的稳定性,从而保证所存储的模式能最终成为GAM的稳定点;其次,通过引入一般相似性测度进一步提出广义GAM模型（G-GAMs）框架,使得GAM模型成为其特例;最后,将GAM模型应用于单样本图像识别,计算机模拟证实了该模型的鲁棒性能。