一种生长型自组织神经网络的聚类研究

自组织特征映射神经网络SOM(Self-Organizing Feature Maps)是一种优良的聚类工具,但其存在着一些限制,如需要预先定义网络大小、网络的收敛性较差和结构不灵活等.为了克服这些不足,在自组织神经网络理论的指导下,提出了一种基于生长型自组织神经网络的聚类方法.在无监督的情况下,该方法采用阈值控制的触发机制实现网络中神经元的生长和删除,并通过神经元权值的有效调整,以期得到数据对象的聚类结果.实验以二维空间中的数据对象为输入样本,验证了该方法的有效性和优越性.     

A Novel Self-Organizing Neural Network for Motion Segmentation

Many computer vision techniques, above all for structure from motion problems, require a segmentation of the images captured by one or more cameras. This paper deals with the segmentation based on the motion information, but can be easily extended to other cases (color, texture and so on). A new neural network, the EXIN Segmentation Neural Network (EXIN SNN) is here introduced. It is incremental, self-organizing and considers its task as the solution of a pattern recognition problem. This original approach overcomes the limits of the traditional segmentation techniques, namely the need of a spatial support for the image objects and the translation parallel to the image plane for the objects in the scene. Examples are given both for synthetic and real images.     

Design for Self-Organizing Fuzzy Neural Networks Based on Genetic Algorithms

A novel hybrid learning algorithm based on a genetic algorithm to design a growing fuzzy neural network, named self-organizing fuzzy neural network based on genetic algorithms (SOFNNGA), to implement Takagi-Sugeno (TS) type fuzzy models is proposed in this paper. A new adding method based on geometric growing criterion and the epsiv-completeness of fuzzy rules is first used to generate the initial structure. Then a hybrid algorithm based on genetic algorithms, backpropagation, and recursive least squares estimation is used to adjust all parameters including the number of fuzzy rules. This has two steps: First, the linear parameter matrix is adjusted, and second, the centers and widths of all membership functions are modified. The GA is introduced to identify the least important neurons, i.e., the least important fuzzy rules. Simulations are presented to illustrate the performance of the proposed algorithm     

Adaptive Fuzzy Neural Network Control Design via a T–S Fuzzy Model for a Robot Manipulator Including Actuator Dynamics

This paper focuses on the development of adaptive fuzzy neural network control (AFNNC), including indirect and direct frameworks for an $n$-link robot manipulator, to achieve high-precision position tracking. In general, it is difficult to adopt a model-based design to achieve this control objective due to the uncertainties in practical applications, such as friction forces, external disturbances, and parameter variations. In order to cope with this problem, an indirect AFNNC (IAFNNC) scheme and a direct AFNNC (DAFNNC) strategy are investigated without the requirement of prior system information. In these model-free control topologies, a continuous-time Takagi–Sugeno (T–S) dynamic fuzzy model with online learning ability is constructed to represent the system dynamics of an $n$-link robot manipulator. In the IAFNNC, an FNN estimator is designed to tune the nonlinear dynamic function vector in fuzzy local models, and then, the estimative vector is used to indirectly develop a stable IAFNNC law. In the DAFNNC, an FNN controller is directly designed to imitate a predetermined model-based stabilizing control law, and then, the stable control performance can be achieved by only using joint position information. All the IAFNNC and DAFNNC laws and the corresponding adaptive tuning algorithms for FNN weights are established in the sense of Lyapunov stability analyses to ensure the stable control performance. Numerical simulations and experimental results of a two-link robot manipulator actuated by dc servomotors are given to verify the effectiveness and robustness of the proposed methodologies. In addition, the superiority of the proposed control schemes is indicated in comparison with proportional–differential control, fuzzy-model-based control, T–S-type FNN control, and robust neural fuzzy network control systems.      

Self-Organizing Transient Chaotic Neural Network for Cellular Channel Assignment

This paper presents a self-organizing transient chaotic neural network to solve the channel assignment problem, one of NP-complete problems. The proposed neural network consists of two parts. The first part is the self-organizing evolution stage, which based on the mutual inhibition mechanisms of bristle differentiation and the problem's heuristic information. The second part is the transient chaotic neural network executing stage. A significant property of the TCNN model is that the chaotic neurodynamics is temporarily generated for searching and self-organizing in order to escape the local minima. In the proposed neural network, the first part is used to improve the quality of the obtained solutions. The simulating results have shown that the self-organizing transient chaotic neural network improves greatly performance through solving the well-known benchmark problems, especially for the Sivarajan's and Kunz's benchmark problems, while the performance is comparable with existing algorithms.     

Self-Organizing and Self-Evolving Neurons: A New Neural Network for Optimization

A self-organizing and self-evolving agents (SOSENs) neural network is proposed. Each neuron of the SOSENs evolves itself with a simulated annealing (SA) algorithm. The self-evolving behavior of each neuron is a local improvement that results in speeding up the convergence. The chance of reaching the global optimum is increased because multiple SAs are run in a searching space. Optimum results obtained by the SOSENs are better in average than those obtained by a single SA. Experimental results show that the SOSENs have less temperature changes than the SA to reach the global minimum. Every neuron exhibits a self-organizing behavior, which is similar to those of the self-organizing map (SOM), particle swarm optimization (PSO), and self-organizing migrating algorithm (SOMA). At last, the computational time of parallel SOSENs can be less than the SA     

Fuzzy Inference Neural Network for Fuzzy Model Tuning

In fuzzy modeling, it is relatively easy to manually define rough fuzzy rules for a target system by intuition. It is, however, time-consuming and difficult to fine-tune them to improve their behavior. This paper describes a tuning method for fuzzy models which is applicable regardless of the form of fuzzy rules and the used defuzzification method. For this purpose, this paper proposes a fuzzy neural network model which can embody fuzzy models. The proposed model provides the functions to perform fuzzy inference and to tune the parameters for the shape of antecedent linguistic terms, the relative importance degrees of rules, and the relative importance degrees of antecedent linguistic terms in rules. In addition, to show its applicability, we perform some experiments and present the results     

A Type-2 Self-Organizing Neural Fuzzy System and Its FPGA Implementation

This paper proposes a type-2 self-organizing neural fuzzy system (T2SONFS) and its hardware implementation. The antecedent parts in each T2SONFS fuzzy rule are interval type-2 fuzzy sets, and the consequent part is of Mamdani type. Using interval type-2 fuzzy sets in T2SONFS enables it to be more robust than type-1 fuzzy systems. T2SONFS learning consists of structure and parameter identification. For structure identification, an online clustering algorithm is proposed to generate rules automatically and flexibly distribute them in the input space. For parameter identification, a rule-ordered Kalman filter algorithm is proposed to tune the consequent-part parameters. The learned T2SONFS is hardware implemented, and implementation techniques are proposed to simplify the complex computation process of a type-2 fuzzy system. The T2SONFS is applied to nonlinear system identification and truck backing control problems with clean and noisy training data. Comparisons between type-1 and type-2 neural fuzzy systems verify the learning ability and robustness of the T2SONFS. The learned T2SONFS is hardware implemented in a field-programmable gate array chip to verify functionality of the designed circuits.      

联合模糊逻辑和神经网络的网络选择算法

在网络优化选择问题的研究中,针对异构网络环境下的网络选择的问题,由于网络性能存在差异,提出一种联合模糊逻辑和神经网络的自适应网络选择算法.由于新方法具有学习训练的能力,所以能够根据输出误差对模糊神经网络的隶属度函数的参数进行动态的在线调整,从而使用户选择最优的网络.最后将联合模糊逻辑和神经网络的网络选择算法与基于模糊逻辑的网络选择算法进行了比较.仿真结果表明,改进方法能有效的保证用户舒适度比率趋于期望的理想值,实现了最优的网络接入选择,减少了乒乓效应发生的次数,并且相较于不自适应调整的模糊逻辑算法有更高的用户舒适度比率.     

Fuzzy Neural Network Models for Classification

In this paper, we combine neural networks with fuzzy logic techniques. We propose a fuzzy-neural network model for pattern recognition. The model consists of three layers. The first layer is an input layer. The second layer maps input features to the corresponding fuzzy membership values, and the third layer implements the inference engine. The learning process consists of two phases. During the first phase weights between the last two layers are updated using the gradient descent procedure, and during the second phase membership functions are updated or tuned. As an illustration the model is used to classify samples from a multispectral satellite image, a data set representing fruits, and Iris data set.     

基于LabVIEW的自组织网络的实现与应用

文章介绍了自组织神经网络在故障诊断方面的应用原理,针时自组织神经网络实现问题提出了一种通过在LabVIEW调用MATLAB应用程序实现自组织神经网络的方法.并通过轴承故障诊断的实例,证明了这种方法的有效性.     

一种广义模糊神经网络的参数解耦学习算法

对于强非线性系统采用分段建模十分有效,广义模糊神经网络能实现这种思想。在此基础上,给出一种模糊规则前、后件参数可分别进行学习的算法,仿真结果表明该方法拟合能力强、学习效率高。     

模糊神经网络的DNA算法训练

提出了基于DNA计算和遗传算法的DNA遗传算法,给出了DNA遗传算法的结构，讨论了遗传操作算子,利用DNA遗传算法对FNN进行学习，比采用梯度型算法和遗传算法有更高的学习精度和更快的收敛速度,该算法有全局收敛性避免了采用梯度型学习算法训练FNN时固有的局部收敛问题，同样，该算法加速了FNN的训练，能够在线应用．     

SCARA机器人自组织模糊聚类神经网络控制器

本文提出了用于SCARA机器人运动控制的自组织模糊聚类神经网络控制器.该控制器基于模糊聚类方法在学习模糊规则之前先优化训练数据,去除冗余数据并解决数据冲突问题,不但减少了神经网络的计算负担,而且生成的规则更加适合机器人运动控制.控制器主要特点是能够动态地自组织结构,学习速度快,鲁棒性强.仿真结果表明控制效果很好.     

基于模糊神经网络的非线性系统模型的辨识

该文提出一种非线性系统的模型辨识方法．利用关系聚类法来进行结构辨识,从而自动获得模糊规则库,并可以得到模糊系统的初始参数,在聚类的基础上,构造一个与之相匹配的模糊神经网络,用它的学习算法来训练网络,得到一个精确的模糊模型,从而实现参数辨识,通过对两个非线性系统辨识的仿真结果验证了该方法的有效性。     

自组织特征映射网络在舌边数据分类中的应用

尝试利用自组织特征映射网络较强的聚类功能对分割出的舌体边缘进行分类。通过实验证明它能很好的将舌边数据分成舌根、舌尖、舌左、舌右四类点,达到预定目标。     

A Lamarckian Approach for Neural Network Training

In Nature, living beings improve their adaptation to surrounding environments by means of two main orthogonal processes: evolution and lifetime learning. Within the Artificial Intelligence arena, both mechanisms inspired the development of non-orthodox problem solving tools, namely: Genetic and Evolutionary Algorithms (GEAs) and Artificial Neural Networks (ANNs). In the past, several gradient-based methods have been developed for ANN training, with considerable success. However, in some situations, these may lead to local minima in the error surface. Under this scenario, the combination of evolution and learning techniques may induce better results, desirably reaching global optima. Comparative tests that were carried out with classification and regression tasks, attest this claim. This revised version was published online in June 2006 with corrections to the Cover Date.     

Neural Network Training System for Marker Encoding

Journal of Computer and Systems Sciences International - In this paper, we propose a training system for visual markers that provides the generation and subsequent recognition (under real-world...     

基于模糊神经网络的倒立摆非线性系统分析

倒立摆系统以其自身的不稳定性而难以控制,也因此成为自动控制实验中验证控制策略优劣的极好的实验装置;针对倒立摆系统的平衡控制问题,提出了用一种应用神经网络来控制倒立摆的方法,同时由于神经元网络的训练的反复性,因此在系统中加入一个模糊控制器,来对神经网络输出的控制变量进行补偿,使神经元网络训练的权值能够始终保持在某一稳定值,从而保证了控制器稳定,仿真实验结果表明采用该方法设计的并联型模糊神经网络控制器对倒立摆这一先天不稳定的系统具有理想的控制效果。     

模糊神经网络PID控制在焊缝跟踪中的应用

1 Introduction Real- time seam tracking is the key step for welding automation. Because welding itself is a complex process, the factors that affect the welding have uncertainty and non - linear characters. Therefore, classical control in seam tracking cannot carry a satisfying result. In latter- day, Fuzzy mathematic and Neural Network appearance, being used on uncertain nonlinear system, and have a good effect. The hybrid controller, which combines Fuzzy con- trol and PID control, uses F…