带参数聚合算子的模糊联想记忆网络

基于最大运算Max和t--范数T的神经网络模型Max-T FAM是B.Kosko提出的经典模糊联想记忆(FAM)网络的一种重要的广义形式,其性能有多处不足.本文利用一种参数化聚合算子∨λ,提出了一种计算简单、易于硬件实现的广义模糊联想记忆(GFAM)网络,其连接算子从{∨λ|λ∈[0,1]}中选取;从理论上严格证明了GFAM具有一致连续性,比所有Max-T FAM的映射能力和存储能力强很多;接着运用模糊关系方程理论提出和分析了GFAM的一种所谓的Max-Min-λ学习算法;最后用实验对GFAM和Max-T FAM的完整可靠存储能力进行了比较,并示例了GFAM在图像联想方面的应用.     

训练模式的摄动对最大—乘积型模糊联想记忆网络的影响

首先建立了前馈型模糊联想记忆网络对训练模式摄动的鲁棒性概念,分析了最大-乘积型模糊联想记忆网络(Max-Product FAM),发现当采用模糊赫布学习算法时它的鲁棒性好,但采用另一学习算法时鲁棒性较差.最后用实验验证了理论结果.     

训练模式的摄动对最大一乘积型模糊联想记忆网络的影响

首先建立了前馈型模糊联想记忆网络对训练模式摄动的鲁棒性概念，分析了最大一乘积型模糊联想记忆网络（Max-Product FAM），发现当采用模糊赫布学习算法时它的鲁棒性好，但采用另一学习算法时鲁棒性较差。最后用实验验证了理论结果。     

模糊联想记忆对训练模式对摄动的鲁棒性研究

基于模糊取大算子（V）和T-模的模糊合成,构建了一类模糊联想记忆网络（V-T FAM）。利用T-模的模糊蕴涵算子,给出了这类V-T FAM的学习算法。针对训练模式对小幅摄动可能对模糊神经网络的性能产生副作用,提出V-T FAM对训练模式对摄动的鲁棒性概念。理论研究表明,当T-模满足Lipschitz条件时,采用上述学习算法的V-T FAM对训练模式对摄动幅度,在系数为β的条件下全局拥有好的鲁棒性。最后用V-T FAM在图像联想方面的实验验证了理论结果。     

一种参数化模糊联想记忆网络的鲁棒性分析

基于最大运算Max以及带参数ξ的t-模Tξ的模糊关系合成,提出一种参数化的广义模糊联想记忆网络Max-Tξ FAM及一种有效学习算法。由于Tξ中参数ξ的作用,在应用中Max-Tξ FAM有更大的适应性和灵活性。从理论上证明采用该学习算法时,对任意 ,Max-Tξ FAM对训练模式摄动的鲁棒性差。通过一个图像联想方面的实验检验了该结论的正确性。     

基于FAM的模糊神经控制器的研究

根据模糊联想记忆(FAM)理论, 提出了预解模糊FAM原理, 给出了预解模糊FAM和一般FAM的等价性的构造性证明. 为了提高FAM推理过程的自适应能力, 将神经网络应用于预解模糊FAM推理, 提出了一种新的智能控制器——FAM神经控制器(FAMNC), 以小车倒立摆为控制对象进行了仿真研究, 表明了所提方法的可行性.     

基于三角模的模糊联想记忆网络

当T为t-模时,基于模糊取大和T的模糊联想记忆网络(FAM)存在局限性,当T为三角模,是t-模的广义形式,将这种FAM推广成基于Max-T的模糊联想记忆网络Max-TFAM.则Max-TFAM实现了从一个向量空间到另一向量空间的映射,从Max-TFAM的值域角度,分析了它的存储能力,并建立了一个三角模T的伴随蕴涵算子新概念,利用该伴随蕴涵算子,在无需T为连续的、严格增等条件下,提出了Max-TFAM的一个简洁的通用离线学习算法和通用在线学习算法.从理论上严格证明了只要Max-TFAM能完整可靠地存储所给的多个模式对,则这两种算法都能轻易找到使得网络能完整可靠存储这些模式对的所有连接权矩阵的最大者.最后,用实验证明了Max-TFAM模型和所提出的学习算法的有效性.     

模糊联想记忆网络对模式摄动的鲁棒性分析

在实际问题中,所获取的模糊神经网络的训练模式对总与客观真实的模式对存在一定的小幅误差（摄动）,从而可能导致对某些输入网络的实际输出与期望输出有很大的误差．为此,本文提出了训练模式集摄动对模糊联想记忆网络(FAM)的鲁棒性概念,并具体讨论了采用一种新的权值学习算法时FAM的这种鲁棒性及其控制方法。最后通过实验证明了采用这种新的权值学习算法时,FAM对模式摄动不会拥有好的鲁棒性。     

模糊联想记忆网络的模式摄动影响研究

本文利用基于三角模的联想记忆网络的性质以及模糊联想记忆网络的全局鲁棒性定义,研究了训练模式集的摄动对模糊联想记忆网络的影响,并对基于几种算子的模糊联想记忆网络在训练模式存在摄动的情况下的受影响程度进行了比较。     

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 .     

模糊联想记忆网络的全局鲁棒性研究——基于爱因斯坦t-模

利用三角模的模糊联想记忆网络的性质以及模糊联想记忆网络的鲁棒性定义,对基于爱因斯坦t-模构建的模糊双向联想记忆网络的学习算法的全局鲁棒性进行了分析。从理论上证明了当训练模式的摄动为正向摄动时,该学习算法可以保持良好的鲁棒性,并用实验验证了该结论;而当摄动存在负向波动时该学习算法不满足全局鲁棒性。然后又进一步对训练模式集摄动最大摄动与输出模式集的最大摄动之间的关系进行研究,得出了训练模式集的最大摄动与输出模式集的最大摄动之间的关系曲线。     

最大-乘积模糊联想记忆的神经网络学习算法

在模糊系统中,从某种意义上说,乘积关系编码可以比最小关系编码保留更多的信息。提出了最大乘积模糊联想记忆的一种新的神经网络学习算法,并给出了严格的理论证明。该算法能够将多个模糊模式对可靠地编码存储到尽可能少的连接权矩阵中,从而大大地减少存储空间,而且容易实现,并举例验证了它的有效性。     

模糊形态联想记忆网络抗随机噪声研究及应用

利用灰度图像分解的思想,结合模糊形态联想记忆网络的方法,提高了模糊形态联想记忆网络对随机噪声的抗噪能力。成功地解决了灰度图像在含有随机噪声时的模糊联想记忆问题,并把该方法推广到对彩色图像的处理,从而给出了一种较好地恢复含噪灰度图像和彩色图像的途径。通过实验,验证了该方法的良好性能,取得了较理想的结果。     

On new fuzzy morphological associative memories

In this paper, the new fuzzy morphological associative memories (FMAMs) based on fuzzy operations (/spl and/,/spl middot/) and (/spl or/,/spl middot/) are presented. FMAM with (/spl or/,/spl middot/) is extremely robust for dilative noise and FMAM with (/spl and/,/spl middot/) is extremely robust for erosive noise. Autoassociative FMAM has the unlimited storage capability and can converge in one step. The convex autoassociative FMAM can be used to achieve a reasonable tradeoff for the mixed noise. Finally, comparisons between autoassociative FMAM and the famous FAM are discussed. FMAM, as another new encoding way of fuzzy rules, still has a multitude of open problems worthy to explore in the future.     

The Kosko Subsethood Fuzzy Associative Memory (KS-FAM): Mathematical Background and Applications in Computer Vision

Many well-known fuzzy associative memory (FAM) models can be viewed as (fuzzy) morphological neural networks (MNNs) because they perform an operation of (fuzzy) mathematical morphology at every node, possibly followed by the application of an activation function. The vast majority of these FAMs represent distributive models given by single-layer matrix memories. Although the Kosko subsethood FAM (KS-FAM) can also be classified as a fuzzy morphological associative memory (FMAM), the KS-FAM constitutes a two-layer non-distributive model. In this paper, we prove several theorems concerning the conditions of perfect recall, the absolute storage capacity, and the output patterns produced by the KS-FAM. In addition, we propose a normalization strategy for the training and recall phases of the KS-FAM. We employ this strategy to compare the error correction capabilities of the KS-FAM and other fuzzy and gray-scale associative memories in terms of some experimental results concerning gray-scale image reconstruction. Finally, we apply the KS-FAM to the task of vision-based self-localization in robotics.     

DEMON-BASED ASSOCIATIVE MEMORIES

Associative memories are of two fundamental types, those that store representations of prototypical patterns (auto-associative memories)and those that store associations between pairs of arbitrary patterns (hetero-associative memories)Four network models of the latter type, each employing a single layer of linear threshold units are presented. Two of these models maintain fixed arrangements of their components. The other two are dynamically self-organizing. They employ feedback about performance to guide changes in the organization of their components. These models are evaluated in terms of storage capacity, error-tolerance, and storage space efficiency. One form of dynamic memory has the highest storage capacity of any known network model of associative memory. A discussion of models by Anderson and Hopfield and some implications of static and dynamic architectures conclude the paper.     

Generic form feature recognition and operation selection using connectionist modelling

For the purpose of enhancing the adaptability of computer-aided process planning systems, two connectionist modelling methods, namely neocognitron (i.e. neural network modelling for pattern recognition) and fuzzy associative memories (FAM), are applied to the phases of feature recognition and operation selection respectively in order to provide the system with the ability of self-learning and the ability to integrate traditional expert planning systems with connectionism-based models. In this paper, the attributed adjacency graph (AAG) extracted from a (B-Rep) solid model is converted to attributed adjacency matrices (AAM) that can be used as input data for the neocognitron to train and recognize feature patterns. With this technique, the system can not only self-reconstruct its recognition abilities for new features by learning without a priori knowledge but can also recognize and decompose intersection features. A fuzzy connectionist model, which is created using the Hebbian fuzzy learning algorithm, is employed subsequently to map the features to the appropriate operations. As the algorithm is capable of learning from rules, it is much easier to integrate the proposed model with conventional expert CAPP systems so that they become more generic in dealing with uncertain information processing and perform knowledge updating. mg]Keywords mw]Computer-aided process planning mw]feature recognition mw]neural networks mw]fuzzy neural networks mw]operation selection mw]connectionist model mw]fuzzy associative memories     

基于爱因斯坦t-模的模糊联想记忆的学习算法

为神经网络提供有效学习算法是神经网络研究的关键问题。文章利用t-模的伴随蕴涵算子,为基于Max和Tes合成的模糊联想记忆网络Max-TesFAM提供了一种新的学习算法,此处Tes是由爱因斯坦提出的一种t-模算子。从理论上严格证明了,只要Max-TesFAM能完整可靠地存储所给的多个模式对,则该新的学习算法一定能找到使得网络能完整可靠存储这些模式对的所有连接权矩阵的最大者。最后,用实验说明了所提出的学习算法的有效性。