基于复合正交神经网络的自适应逆控制系统

目前，在自适应逆控制系统中常采用BP神经网络，而BP网络存在算法复杂、易陷入局部极小解等不足。而正交神经网络能克服BP网络的不足，但由于正交神经网络学习算法存在某些局限性，提出了一种复合正交神经网络，该正交网络结构与三层前向正交网络相同，不同的是正交网络的隐单元处理函数采用带参数的Sigmoid函数的复合正交函数，该神经网络算法简单，学习收敛速度快，并能对网络的函数参数进行优化，为非线性系统的动态建模提供了一种方法。仿真实验表明，网络在用于过程的自适应逆控制中具有很高的控制精度和自适应学习能力。该动态神经网络比其它神经网络具有更强的建模能力与学习适应性，有线性、非线性逼近精度高等优异特性，非常适合于实时控制系统。     

再励学习及其在移动机器人行为规划中的应用

再励学习（Reinforcement Learning,RL）是一种成功地结合动态编程和控制问题的机器智能方法,它将动态编程和有监督学习方法结合到机器学习系统中,通常用于解决预测和控制两类问题。提出了以矢量形式表示的评估函数,为了实现多维再励学习,用一专门的神经网络（Q网络）实现评判网络,研究其在移动机器人行为规划中的应用。     

通用型多语竞争与政策调控复杂Agent网络模型

利用基于社会圈子理论的agent微观建模技术来构建语言竞争社会网络。构建的网络拓扑结构参数更接近实际社会网络参数,agent可以赋予空间属性,可以描述混合居住和分片聚居社会网络,而且具有动态特性。以三语竞争为例,提出了一种将网络中个体间的三语竞争分解为三个两种语言竞争的问题,给出了一种基于竞争原理的通用多语竞争复杂agent网络仿真建模方法。网络上的节点agent代表具有学习和遗忘功能的个体,每个个体均可以通过学习获得第二或第三种语言成为双语或三语者,也可以通过遗忘重新成为单语或双语者,同时agent考虑了语言的垂直传播。分析了语言地位、不同语言人口比例、移动人口比例、社会半径、不同语言人口的空间居住模式、语言传承率等因素及其综合调控措施对语言竞争的影响。仿真分析表明,该模型贴近实际社会,为多语竞争提供依据。     

基于神经网络的交互式自动获取知识的N—R方法

本文为解决知识系统构造过程中瓶颈问题－－知识获取，提出了一种基于神经网络ＮＮ的自动获取多级推理产生规则的Ｎ－４方法，该方法采用了特有的ＮＮ结构模型和相应的学习算法，使得ＮＮ在学习过程中动态确定隐层节点数的同时，也产生了样例集中没有定义的新概念，学习后的ＮＮ能用本文提出的转换算法转换成推理网络，最终方便地得到了产生式规则集。     

基于神经网络的交互式自动获取知识的N－R方法

本文为解决知识系统构造过程中的瓶颈问题──知识获取，提出了一种基于神经网络ＮＮ（ｎｅｕｒａｌｎｅｔｗｏｒｋ）的自动获取多级推理产生式规则的Ｎ－Ｒ方法，该方法采用了特有的ＮＮ结构模型和相应的学习算法，使得ＮＮ在学习过程中动态确定隐层节点数的同时，也产生了样例集中没有定义的新概念，学习后的ＮＮ能用本文提出的转换算法转换成推理网络，最终方便地得到产生式规则集.     

一种新的双向联想记忆的学习算法

提出了一种新的用于双向联想记忆的学习算法，该算法利用了输入向量各元素之间的关联信息，在联想的过程中，动态地调整权值矩阵，增强了网络适应能力，利用了更多的已知信息，从而提高了网络的性能．     

神经网络集成在图书剔旧分类中的应用

在分析图书剔旧工作的基础上，指出用智能的方法解决图书剔旧问题的必要性。提出了可以用神经网络集成技术来解决该问题，并给出一种动态构建神经网络集成的方法，该方法在训练神经网络集成成员网络时不仅调整网络的连接权值，而且动态地构建神经网络集成中各成员神经网络的结构，从而在提高单个网络精度的同时，增加了各网络成员之间的差异度，减小了集成的泛化误差。实验证明该方法可以有效地用于图书剔旧分类。     

图象压缩的模糊竞争矢量量化方法

在分析神经网络竞争学习算法和模糊Ｃ均值算法的基础上，提出了模糊竞争学习算法，并对模糊隶属度函数进行了探讨。理论分析和实验结果表明，模糊竞争学习算法用于图象矢量量化压缩编码是一种非常有效的方法。     

一种基于神经网络的模糊推理和规则生成方法

文章介绍一种基于神经网络的模糊推理和规则生成方法,该方法在构造网络时能辨识网络结构和参数,且需要很少的先验信息;文章提出一种混合学习方法,该学习方法分两阶段进行学习,第一阶段使用一种改进的竞争学习方法,建立模糊规则。第二阶段,通过梯度下降技术,来优化模糊规则的参数,以达到高性能的模型。学习后的网络,模糊推理系统的参数融于在网络的拓扑中。文章还给出实验数据。     

模糊系统反向传播学习算法在系统辨识中的应用

文中提出了一种模糊逻辑系统的网络模型，给出了相应的反向传播学习算法，并将其用于非线 辨识，构造了于种动态辨识器。     

Improving information-theoretic competitive learning by accentuated information maximization

In this paper, we propose a new computational method for information-theoretic competitive learning. We have so far developed information-theoretic methods for competitive learning in which competitive processes can be simulated by maximizing mutual information between input patterns and competitive units. Though the methods have shown good performance, networks have had difficulty in increasing information content, and learning is very slow to attain reasonably high information. To overcome the shortcoming, we introduce the rth power of competitive unit activations used to accentuate actual competitive unit activations. Because of this accentuation, we call the new computational method “accentuated information maximization”. In this method, intermediate values are pushed toward extreme activation values, and we have a high possibility to maximize information content. We applied our method to a vowel–consonant classification problem in which connection weights obtained by our methods were similar to those obtained by standard competitive learning. The second experiment was to discover some features in a dipole problem. In this problem, we showed that as the parameter r increased, less clear representations could be obtained. For the third experiment of economic data analysis, much clearer representations were obtained by our method, compared with those obtained by the standard competitive learning method.     

Supposed maximum information for comprehensible representations in SOM

In this paper, we propose a new information-theoretic method to simplify the computation of information and to unify several methods in one framework. The new method is called “supposed maximum information,” used to produce humanly comprehensible representations in competitive learning by taking into account the importance of input units. In the new learning method, by supposing the maximum information of input units, the actual information of input units is estimated. Then, the competitive network is trained with the estimated information in input units. The method is applied not to pure competitive learning, but to self-organizing maps, because it is easy to demonstrate visually how well the new method can produce more interpretable representations. We applied the method to three well-known sets of data, namely, the Kohonen animal data, the SPECT heart data and the voting data from the machine learning database. With these data, we succeeded in producing more explicit class boundaries on the U-matrices than did the conventional SOM. In addition, for all the data, quantization and topographic errors produced by our method were lower than those by the conventional SOM.     

基于模糊竞争学习的非线性系统自适应模糊建模方法

提出了一种新的基于模糊竞争学习的自调整的模糊建模方法. 基于模糊竞争学习, 模糊系统能够进行自适应模糊推理. 在被调整模糊系统基础上, 提出了一种非线性系统在线估计参数的在线辨识算法. 为了证明提出算法的有效性, 最后给出了几个例子的仿真结果.     

Repeated comprehensibility maximization in competitive learning

In this study, we propose a new type of information-theoretic method in which the comprehensibility of networks is progressively improved upon within a course of learning. The comprehensibility of networks is defined by using mutual information between competitive units and input patterns. When comprehensibility is maximized, the most simplified network configurations are expected to emerge. Comprehensibility is defined for competitive units, and the comprehensibility of the input units is measured by examining the comprehensibility of competitive units, with special attention being paid to the input units. The parameters to control the values of comprehensibility are then explicitly determined so as to maximize the comprehensibility of both the competitive units and the input units. For the sake of easy reproducibility, we applied the method to two problems from the well-known machine learning database, namely, the Senate problem and the cancer problem. In both experiments, any type of comprehensibility can be improved upon, and we observed that fidelity measures such as quantization errors could also be improved.     

Energy based competitive learning

This paper addresses the three important issues associated with competitive learning clustering, which are auto-initialization, adaptation to clusters of different size and sparsity, and eliminating the disturbance caused by outliers. Although many competitive learning methods have been developed to deal with some of these problems, few of them can solve all the three problems simultaneously. In this paper, we propose a new competitive learning clustering method termed energy based competitive learning (EBCL) to simultaneously tackle these problems. Auto-initialization is achieved by extracting samples of high energy to form a core point set, whereby connected components are obtained as initial clusters. To adapt to clusters of different size and sparsity, a novel competition mechanism, namely, size-sparsity balance of clusters (SSB), is developed to select a winning prototype. For eliminating the disturbance caused by outliers, another new competition mechanism, namely, adaptive learning rate based on samples' energy (ALR), is proposed to update the winner. Data clustering experiments on 2000 simulated datasets comprising clusters of different size and sparsity, as well as with outliers, have been performed to verify the effectiveness of the proposed method. Then we apply EBCL to automatic color image segmentation. Comparison results show that the proposed EBCL outperforms existing competitive learning algorithms.     

Incremental maximum margin clustering

This paper proposes incremental maximum margin clustering in which one data point at a time is examined to decide which cluster the new data point belongs. The proposed method adopts the off-line iterative maximum margin clustering method’s alternating optimization algorithm. Accurate online support vector regression is employed in the alternating optimization. To avoid premature convergence, a sequence of decremental unlearning and incremental learning steps is performed. The proposed method is experimentally argued to (i) be scalable and competitive on training time front when compared with iterative maximum margin clustering and (ii) achieve competitive cluster quality compared to the off-line counterpart.     

Multi-instance classification based on regularized multiple criteria linear programming

Regularized multiple criteria linear programming (RMCLP) model is a new powerful method for classification and has been used in various real-life data mining problems. In this paper, a new Multi-instance Classification method based on RMCLP was proposed (called MI-RMCLP), which includes two algorithms for linearly separable case and nonlinearly case separately. The key point of this method, instead of a mixed integer quadratic programming in MI-SVM, is that it is able to deal with multi-instance learning problem by an iterative strategy solving sequential quadratic programming problems. All experiment results have shown that MI-RMCLP method can converge to the optimal value in limited iterative steps and be a competitive method in multi-instance learning classification.     

Double enhancement learning for explicit internal representations: unifying self-enhancement and information enhancement to incorporate information on input variables

In this paper, we propose a new type of information-theoretic method called “double enhancement learning,” in which two types of enhancement, namely, self-enhancement and information enhancement, are unified. Self-enhancement learning has been developed to create targets spontaneously within a network, and its performance has proven to be comparable with that of conventional competitive learning and self-organizing maps. To improve the performance of the self-enhancement learning, we try to include information on input variables in the framework of self-enhancement learning. The information on input variables is computed by information enhancement in which a specific input variable is used to enhance competitive unit outputs. This information is again used to train a network with the self-enhancement learning. We applied the method to three problems, namely, an artificial data, a student survey and the voting attitude problem. In all three problems, quantization errors were significantly decreased with the double enhancement learning. The topographic errors were relatively higher, but the smallest number of topographic errors was also obtained by the double enhancement learning. In addition, we saw that U-matrices for all problems showed explicit boundaries reflecting the importance of input variables.     

The Softmap Algorithm

A new unsupervised competitive learning rule is introduced, called the Self-organizing free-topology map (Softmap) algorithm, for nonparametric density estimation. The receptive fields of the formal neurons are overlapping, radially-symmetric kernels, the radii of which are adapted to the local input density together with the weight vectors which define the kernel centers. A fuzzy code membership function is introduced in order to encompass, in a novel way, the presence of overlapping receptive fields in the competitive learning scheme. Furthermore, a computationally simple heuristic is introduced for determining the overall degree of smoothness of the resulting density estimate. Finally, the density estimation performance is compared to that of the variable kernel method, VBAR and Kohonen's SOM algorithm.     

自组织特征映射神经网络的改进及应用研究

为了提高自组织特征映射(SOM)神经网络学习速度及分类精度,对初始连接权值及竞争层神经元数的确定方法进行改进。提出用聚类方法确定初始权值的新方法,还提出了采用聚类数与邻域之和确定竞争层神经元数的方法,并给出了改进后的SOM分类算法。将改进的SOM网络用于储粮害虫分类,采用留一方法进行分类验证实验。仿真结果表明,改进后的SOM网络在学习速度和分类精度方面都有明显提高,证明了该方法的有效性。