模式线性可分时的一种单层感知器算法

在模式识别时常常需要对模式进行分类,线性可分模式的分类是其中最基本的一种.常用的线性分类算法是LMSE算法,它们在本质上都属于几何分类法,当模式线性可分时,一般都能达到令人满意的效果.然而考虑到LMSE算法并非是最简单和有效的线性分类算法,本文基于神经网络中单层感知器的概念,利用单层感知器可以把输入空间划分成两个区域来进行输入向量分类的特点,提出了在模式线性可分时用神经网络中单层感知器进行模式划分的一种新算法.然后对该线性分类算法的原理和算法过程进行了阐述,最后用MATLAB实现了这种分类算法,并解决了两个不同类型的线性模式的划分问题.     

一种基于核函数的非线性感知器算法

为了提高经典Rosenblatt感知器算法的分类能力，该文提出一种基于核函数的非线性感知器算法，简称核感知器算法，其特点是用简单的迭代过程和核函数来实现非线性分类器的一种设计，核感知器算法能够处理原始属性空间中线性不可分问题和高维特征空间中线性可分问题。同时，文中详细分析了其算法与径向基函数神经网络、势函数方法和支持向量机等非线性算法的关系。人工和实际数据的计算结果表明：与线性感知器算法相比，核感知器算法可以有效地提高分类精度。     

软间隔组合凸线性感知器设计

组合凸线性感知器是用来构造分片线性分类器的一个通用理论框架。对于凸可分和叠可分情况,分别使用支持凸线性感知器算法和支持组合凸线性感知器算法将两类样本分开。在此基础上,文中提出一种软间隔的组合凸线性感知器设计方法。该方法首先映射原空间数据到高维特征空间,然后利用K均值算法将其中一类样本聚类成多个簇,并在每一簇与另一类样本间构造凸线性感知器,最后集成组合凸线性感知器。该方法能解决原感知器模型不适用非叠可分数据的问题,并且在一定程度上简化模型结构,在保证分类精度的前提下,提高泛化能力。实验结果证实文中方法的有效性,同其它分片线性分类器的对比也说明了它的优势。     

组合凸线性感知器的极大切割构造方法

组合凸线性感知器（Multiconlitron）是用来构造分片线性分类器的一个通用理论框架,对于凸可分和叠可分情况,分别使用支持凸线性感知器算法（Support conlitron algorithm,SCA）和支持组合凸线性感知器算法（Support multiconlitron algorithm,SMA）将两类样本分开. 本文在此基础上,提出了一种基于极大切割（Maximal cutting）的组合凸线性感知器构造方法. 该方法由两阶段训练构成,第一阶段称为极大切割过程（Maximal cutting process,MCP）,通过迭代不断寻求能够切开最多样本的线性边界,并因此来构造尽可能小的决策函数集,最大程度减少决策函数集中线性函数的数量,最终简化分类模型. 第二阶段称为边界调整过程（Boundary adjusting process,BAP）,对MCP得到的初始分类边界进行一个二次训练,调整边界到适当位置,以提高感知器的泛化能力. 数值实验说明,此方法能够产生更为合理的分类模型,提高了感知器的性能. 同其他典型分片线性分类器的性能对比,也说明了这种方法的有效性和竞争力.     

应用感知器进行模式分类

感知器是一种有用的神经网络模型,可以对线性可分的模式进行正确分类。试验结果表明,该网络模型适用于简单的模式分类问题,具有较好的实用性。     

一种快速的单层感知器网络学习算法

提出了一种单层感知器网络训练的新算法,证明了对于线性可分问题和线性不可分问题,算法总是在有限步内终止,算法的迭代次数以模式数为上界;而且,在算法终止时,对于线性可分问题,总是能得到正确的权向量解,所以,如果在算法结束时还不能划分所有模式,则说明给定的模式集确是不可线性划分的。     

感知器学习算法研究

介绍感知器学习算法及其变种,给出各种感知器算法的伪代码,指出各种算法的优点。给出感知器算法在线性可分和线性不可分情况下的误差界定理,讨论各种感知器学习算法的误差界理论,给出各种算法的误差界。介绍感知器学习算法在在线优化场景、强化学习场景和赌博机算法中的应用,并对未解决的问题进行讨论。     

多层感知器分类行为的模糊线性分析

线性判别函数理论是线性分类器的分析基础,并不适合非线性分类器.本文把非线性激励函数视为隶属度函数,将非线性神经元及多层感知器分类行为的分析建筑在模糊集理论基础上,提出模糊线性判别函数与模糊判别边界、模糊分类等概念.并引出将隐层初始权向量均匀分布在权空间超球面上的初始化方法,明显提高了多层感知器的收敛性能.并提出了一种在多层感知器的类空间中构造最优超平面的简易新方法.     

一种基于函数联接网络的纹理分类方法

提出了一种基于函数联接的感知器神经网络的纹理分类方法,它采用高新－马尔柯夫随机场模型（ＧＭＲＦ）对纹理进行描述,模型参数即为纹理特征,参数估计采用最小平方误差方法获得,将估计参数作为表达纹理的特征向量,用感知器网络对特征进行分类,并且采用函数联接的方式解决线性不可分问题,对纹理图象进行的实验表明,采用这种方法能够提高学习速度,简化计算过程,并取得较好的纹理分类效果。     

多层感知器在提高软件可维护性上的应用

预测分析软件质量可看作是一个以源代码度量作为属性标签、模块性能作为类标签的分类问题。首次提出将多层感知器应用于软件质量预测,并使用对称不定性分析来提高其分类性能。多层感知器是一种利用误差反向传播方法分类实例的分类器,而对称不定性分析可降低算法复杂度并获得更好的分类效果。与其他传统方法相比,基于对称不定性分析的多层感知器的分类效果无论是准确度还是稳定性都是最好的,它能获得对软件质量的最高预测精度,从而有效地提高软件可维护性。     

On the generalization error of fixed combinations of classifiers

We consider the generalization error of concept learning when using a fixed Boolean function of the outputs of a number of different classifiers. Here, we take into account the ‘margins’ of each of the constituent classifiers. A special case is that in which the constituent classifiers are linear threshold functions (or perceptrons) and the fixed Boolean function is the majority function. This corresponds to a ‘committee of perceptrons,’ an artificial neural network (or circuit) consisting of a single layer of perceptrons (or linear threshold units) in which the output of the network is defined to be the majority output of the perceptrons. Recent work of Auer et al. studied the computational properties of such networks (where they were called ‘parallel perceptrons’), proposed an incremental learning algorithm for them, and demonstrated empirically that the learning rule is effective. As a corollary of the results presented here, generalization error bounds are derived for this special case that provide further motivation for the use of this learning rule.     

A multilayer incremental neural network architecture for classification

A new multilayer incremental neural network (MINN) architecture and its performance in classification of biomedical images is discussed. The MINN consists of an input layer, two hidden layers and an output layer. The first stage between the input and first hidden layer consists of perceptrons. The number of perceptrons and their weights are determined by defining a fitness function which is maximized by the genetic algorithm (GA). The second stage involves feature vectors which are the codewords obtained automaticaly after learning the first stage. The last stage consists of OR gates which combine the nodes of the second hidden layer representing the same class. The comparative performance results of the MINN and the backpropagation (BP) network indicates that the MINN results in faster learning, much simpler network and equal or better classification performance.     

Attractor networks for shape recognition

We describe a system of thousands of binary perceptrons with coarse-oriented edges as input that is able to recognize shapes, even in a context with hundreds of classes. The perceptrons have randomized feedforward connections from the input layer and form a recurrent network among themselves. Each class is represented by a prelearned attractor (serving as an associative hook) in the recurrent net corresponding to a randomly selected subpopulation of the perceptrons. In training, first the attractor of the correct class is activated among the perceptrons; then the visual stimulus is presented at the input layer. The feedforward connections are modified using field-dependent Hebbian learning with positive synapses, which we show to be stable with respect to large variations in feature statistics and coding levels and allows the use of the same threshold on all perceptrons. Recognition is based on only the visual stimuli. These activate the recurrent network, which is then driven by the dynamics to a sustained attractor state, concentrated in the correct class subset and providing a form of working memory. We believe this architecture is more transparent than standard feedforward two-layer networks and has stronger biological analogies.     

一种基于LSA和Kohonen网络的文本分类新方法

文中根据隐含语义分析理论(LSA)和Kohonen网络理论提出一种文本分类新方法。应用Kohonen网络进行文本分类存在训练速度慢的缺点，因此在网络训练阶段引入了有监督机制，提高了网络的分类速度和精度；但是对于高维的文本特征向量来说，分类速度很低，甚至应用Kohonen网络进行分类，不能取得理想结果；新方法应用LSA理论来建立文本集的向量空间模型，在词条的权重中引入了语义关系，消减了原词条矩阵中包含的“噪声”因素，从而更加突出了词和文本之间的语义关系。通过奇异值分解(SVD)，有效地降低了向量空间的维数，从而大大提高了文本分类的精度和速度，同时根据因子分析理论给出了维数K的选取方法。     

MISEP method for postnonlinear blind source separation

In this letter, a standard postnonlinear blind source separation algorithm is proposed, based on the MISEP method, which is widely used in linear and nonlinear independent component analysis. To best suit a wide class of postnonlinear mixtures, we adapt the MISEP method to incorporate a priori information of the mixtures. In particular, a group of three-layered perceptrons and a linear network are used as the unmixing system to separate sources in the postnonlinear mixtures, and another group of three-layered perceptron is used as the auxiliary network. The learning algorithm for the unmixing system is then obtained by maximizing the output entropy of the auxiliary network. The proposed method is applied to postnonlinear blind source separation of both simulation signals and real speech signals, and the experimental results demonstrate its effectiveness and efficiency in comparison with existing methods.     

基于多层前馈型人工神经网络的抑郁症分类系统研究

多层前馈型人工神经网络(MLPANN)是应用广泛的一种人工神经网络。该文研究了用于抑郁症中医证候分类的一类MLPANN,设计了一种基于自定义网络结构及其他参数的BP训练算法的分类系统,并首次应用在抑郁症的中医证候分类研究中。该系统利用实际病症样本数据进行了训练和分类,结果表明系统具有很好的分类效果,可以用于指导抑郁症诊断和治疗。     

多层感知器网络内部判决模式的研究

人工神经网络（ANN）内部行为的研究,无论是对生物神经系统内部工作机理、ANN理论,还是对ANN应用都有重要意义。本文在作者原有工作基础上加以发展,针对多层感知器网络应用于模式识别、分类、 数逼近与参数估计的内部行为,作出了明确解释;以单陷层结构为典型,定义了隐层神经元输出为网络输出量的“（正、负）内部分量”,陷层权重分布为网络求解问题的“内部判决模式”;并给出了应用这一理论分析的实例。     

基于神经网络的舰船运动短期预测

船舶在海上航行过程中受海风及海浪等因素的影响，使其产生六自由度的随机复杂运动。这对武器控制、舰载机着舰等操作起着相当的影响。该文分析了舰船运动姿态的时间序列特性，按照动力学系统反演原理，建立基于时间序列的非线性预测映射，根据在理论上三层感知器神经网络能够无限逼近任意非线性函数的特点，建立了用于时序分析的三层感知器模型，给出了时序反向传播算法。并进行了算例计算，从结果分析看，神经网络预测精度要稍高于时间序列分析法，为舰船运动短期预测提供了一种新的方法。     

Breast cancer diagnosis using genetic programming generated feature

This paper proposes a novel method for breast cancer diagnosis using the feature generated by genetic programming (GP). We developed a new feature extraction measure (modified Fisher linear discriminant analysis (MFLDA)) to overcome the limitation of Fisher criterion. GP as an evolutionary mechanism provides a training structure to generate features. A modified Fisher criterion is developed to help GP optimize features that allow pattern vectors belonging to different categories to distribute compactly and disjoint regions. First, the MFLDA is experimentally compared with some classical feature extraction methods (principal component analysis, Fisher linear discriminant analysis, alternative Fisher linear discriminant analysis). Second, the feature generated by GP based on the modified Fisher criterion is compared with the features generated by GP using Fisher criterion and an alternative Fisher criterion in terms of the classification performance. The classification is carried out by a simple classifier (minimum distance classifier). Finally, the same feature generated by GP is compared with a original feature set as the inputs to multi-layer perceptrons and support vector machine. Results demonstrate the capability of this method to transform information from high-dimensional feature space into one-dimensional space and automatically discover the relationship among data, to improve classification accuracy.     

The dynamic model of lateral inhibition network and it is application

Breast cancer is the major cause of cancer deaths in women today and it is the most common type of cancer in women. Many sophisticated algorithm have been proposed for classifying breast cancer data. This paper presents some experiments for classifying breast cancer tumor and proposes the use local linear wavelet neural network for breast cancer recognition by training its parameters using Recursive least square (RLS) approach to improve its performance. The difference of the local linear wavelet network with conventional wavelet neural network (WNN) is that the connection weights between hidden layer and output layer of conventional WNN are replaced by a local linear model. The result quality has been estimated and compared with other experiments. Results on extracted breast cancer data from University of Wisconsin Hospital Madison show that the proposed approach is very robust, effective and gives better classification.