Iterative inversion of fuzzified neural networks

The inversion of a neural network is a process of computing inputs that produce a given target when fed into the neural network. The inversion algorithm of crisp neural networks is based on the gradient descent search in which a candidate inverse is iteratively refined to decrease the error between its output and the target. In this paper. we derive an inversion algorithm of fuzzified neural networks from that of crisp neural networks. First, we present a framework of learning algorithms of fuzzified neural networks and introduce the idea of adjusting schemes for fuzzy variables. Next, we derive the inversion algorithm of fuzzified neural networks by applying the adjusting scheme for fuzzy variables to total inputs in the input layer. Finally, we make three experiments on the parity-three problem, examine the effect of the size of training sets on the inversion, and investigate how the fuzziness of inputs and targets of training sets affects the inversion     

COMPRESSION AND EXPANSION OF FUZZY RULE BASES BY USING CRISP-FUZZY NEURAL NETWORKS

A fuzzy neural network with knowledge discovery FNNKD is designed to perform adaptive compensatory fuzzy reasoning based on more useful and more heuristic primary fuzzy sets. In order to overcome the weakness of the conventional crisp neural network and the fuzzy operation oriented neural network, we have developed a general fuzzy reasoning oriented fuzzy neural network called a crisp-fuzzy neural network CFNN that is capable of extracting high-level knowledge such as fuzzy IF-THEN rules from either crisp data or fuzzy data. A CFNN can effectively compress a 5 5 fuzzy IF-THEN rule base of a cart-pole balancing system to a 3 3 one, then to a 2 2 one, and finally to a 1 1 one, and can expand on invalid sparse 3 3 fuzzy IF-THEN rule base of a cart-pole balancing system to a valid 5 5 one. In addition, a CFNN can control a more complex cart-pole balancing system with random fuzzy noise inputs and outputs i.e., nonconventional using crisp inputs and outputs without any noise . The simulations have indicated that a CFNN is an efficient neurofuzzy system with abilities to discover new fuzzy knowledge from either numerical data or fuzzy data, compress and expand fuzzy knowledge, and do fuzzy reasoning.     

Extracting rules from a (fuzzy/crisp) recurrent neural network using a self‐organizing map

Although the extraction of symbolic knowledge from trained feedforward neural networks has been widely studied, research in recurrent neural networks (RNN) has been more neglected, even though it performs better in areas such as control, speech recognition, time series prediction, etc. Nowadays, a subject of particular interest is (crisp/fuzzy) grammatical inference, in which the application of these neural networks has proven to be suitable. In this paper, we present a method using a self‐organizing map (SOM) for extracting knowledge from a recurrent neural network able to infer a (crisp/fuzzy) regular language. Identification of this language is done only from a (crisp/fuzzy) example set of the language. © 2000 John Wiley & Sons, Inc.     

基于模糊控制律的遗传神经匝道协调控制

讨论了快速路匝道系统中智能控制技术问题。针对匝道系统特点,分析了模糊控制、人工神经网络、遗传算法的适用性,提出了一种基于模糊控制律的遗传神经匝道协调控制方案。在该方案中,对模糊控制输入输出数据进行线性修正,使用修正后的数据完成遗传神经网络训练,并用神经网络代替模糊控制器对匝道系统进行控制。给出了神经网络结构和遗传算法流程,并结合宏观交通流模型进行系统仿真。仿真结果表明,与模糊控制相比,控制效果显著提高。     

基于模糊神经网络的铁路车辆热轴等级判别模型

判别模型。该模型选定了温升、列温升差、辆温升差3个特征作为输入量,4种热轴等级作为输出量,并利用125条模糊推理规则和学习算法对模糊神经网络进行训练,得到的模糊神经网络可作为专家系统对热轴进行判别。实例仿真结果表明:模糊神经网络热轴判别模型使得判别参数减少,判别科学化,且判别的一致率达到95%。     

基于卷积神经网络的微博情感倾向性分析

微博情感倾向性分析旨在发现用户对热点事件的观点态度。由于微博噪声大、新词多、缩写频繁、有自己的固定搭配、上下文信息有限等原因,微博情感倾向性分析是一项有挑战性的工作。该文主要探讨利用卷积神经网络进行微博情感倾向性分析的可行性,分别将字级别词向量和词级别词向量作为原始特征,采用卷积神经网络来发现任务中的特征,在COAE2014任务4的语料上进行了实验。实验结果表明,利用字级别词向量及词级别词向量的卷积神经网络分别取得了95.42%的准确率和94.65%的准确率。由此可见对于中文微博语料而言,利用卷积神经网络进行微博情感倾向性分析是有效的,且使用字级别的词向量作为原始特征会好于使用词级别的词向量作为原始特征。     

QoS组播路由的模糊遗传算法

已有的QoS组播路由算法都假设已知网络全局的精确状态，而且QoS约束都以确定性界限来表达。然而在实际的网络环境中，网络节点根本无法获得网络全局的精确状态．而且QoS约束完全用确定性界限来表达也存在一定的局限性。本文将模糊集合论的基本原理应用于QoS组播路由问题，充分考虑网络节点所获信息的模糊性和随机性，以及QoS约束务件的模糊界限这一客观存在的性质，提出一种新的QoS组播路由的模糊遗传算法FG。仿真实验表明．该算法是可靠且有效的。     

Solving fuzzy shortest path problems by neural networks

In this paper, we introduce the neural networks for solving fuzzy shortest path problems. The penalization of the neural networks is realized after transforming into crisp shortest path model. The procedure and efficiency of this approach are shown with numerical simulations.     

Feedforward networks with fuzzy signals

 The paper discusses feedforward neural networks with fuzzy signals. We analyze the feedforward phase and show some properties of the output function. Then we present a backpropagation like adaptation algorithm for crisp weights, thresholds and neuron slopes of the multilayer network with sigmoidal transfer functions. We provide theoretical justification for the adaptation formulas. The results are of general nature and together with the presented approach can be used for other types of feedforward networks. Proposed and discussed are also applications of the presented feedforward networks.     

Fuzzy ARTMAP: A neural network architecture for incrementalsupervised learning of analog multidimensional maps

A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may represent fuzzy or crisp sets of features. The architecture, called fuzzy ARTMAP, achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Four classes of simulation illustrated fuzzy ARTMAP performance in relation to benchmark backpropagation and generic algorithm systems. These simulations include finding points inside versus outside a circle, learning to tell two spirals apart, incremental approximation of a piecewise-continuous function, and a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE systems and with Simpson's FMMC system.     

A recurrent neural fuzzy network for word boundary detection invariable noise-level environments

This paper discusses the problem of automatic word boundary detection in the presence of variable-level background noise. Commonly used robust word boundary detection algorithms always assume that the background noise level is fixed. In fact, the background noise level may vary during the procedure of recording. This is the major reason that most robust word boundary detection algorithms cannot work well in the condition of variable background noise level. In order to solve this problem, we first propose a refined time-frequency (RTF) parameter for extracting both the time and frequency features of noisy speech signals. The RTF parameter extends the (time-frequency) TF parameter proposed by Junqua et al. from single band to multiband spectrum analysis, where the frequency bands help to make the distinction between speech signal and noise clear. The RTF parameter can extract useful frequency information. Based on this RTF parameter, we further propose a new word boundary detection algorithm by using a recurrent self-organizing neural fuzzy inference network (RSONFIN). Since RSONPIN can process the temporal relations, the proposed RTF-based RSONFIN algorithm can find the variation of the background noise level and detect correct word boundaries in the condition of variable background noise level. As compared to normal neural networks, the RSONFIN can always find itself an economic network size with high-learning speed. Due to the self-learning ability of RSONFIN, this RTF-based RSONFIN algorithm avoids the need for empirically determining ambiguous decision rules in normal word boundary detection algorithms. Experimental results show that this new algorithm achieves higher recognition rate than the TF-based algorithm which has been shown to outperform several commonly used word boundary detection algorithms by about 12% in variable background noise level condition, It also reduces the recognition error rate due to endpoint detection to about 23%, compared to an average of 47% obtained by the TF-based algorithm in the same condition.     

Intelligent leaky bucket algorithms for sustainable-cell-rate usage parameter control in ATM networks

In this paper, we propose two intelligent leaky bucket algorithms for sustainable-cell-rate usage parameter control of multimedia transmission in asynchronous transfer mode networks. One is the fuzzy leaky bucket algorithm, in which a fuzzy increment controller (FIC) is incorporated with the conventional leaky bucket algorithm; the other is the neural fuzzy leaky bucket algorithm, where a neural fuzzy increment controller (NFIC) is added with the conventional leaky bucket algorithm. Both the FIC and the NFIC properly choose the long-term mean cell rate and the short-term mean cell rate as input variables to intelligently determine the increment value. Simulation results show that both intelligent leaky bucket algorithms have significantly outperformed the conventional leaky bucket algorithm, by responding about 160% faster when taking control actions against a nonconforming connection while reducing as much as 50% of the queueing delay experienced by a conforming connection. In addition, the neural fuzzy leaky bucket algorithm outperforms the fuzzy leaky bucket algorithm, in aspects of three performance measures such as selectivity, responsiveness, and queueing delay, especially when the traffic flow is bursty, dynamic, and nonstationary.     

Neural networks that learn from fuzzy if-then rules

An architecture for neural networks that can handle fuzzy input vectors is proposed, and learning algorithms that utilize fuzzy if-then rules as well as numerical data in neural network learning for classification problems and for fuzzy control problems are derived. The learning algorithms can be viewed as an extension of the backpropagation algorithm to the case of fuzzy input vectors and fuzzy target outputs. Using the proposed methods, linguistic knowledge from human experts represented by fuzzy if-then rules and numerical data from measuring instruments can be integrated into a single information processing system (classification system or fuzzy control system). It is shown that the scheme works well for simple examples     

The multisynapse neural network and its application to fuzzyclustering

In this paper, a new neural architecture, the multisynapse neural network, is developed for constrained optimization problems, whose objective functions may include high-order, logarithmic, and sinusoidal forms, etc., unlike the traditional Hopfield networks which can only handle quadratic form optimization. Meanwhile, based on the application of this new architecture, a fuzzy bidirectional associative clustering network (FBACN), which is composed of two layers of recurrent networks, is proposed for fuzzy-partition clustering according to the objective-functional method. It is well known that fuzzy c-means is a milestone algorithm in the area of fuzzy c-partition clustering. All of the following objective-functional-based fuzzy c-partition algorithms incorporate the formulas of fuzzy c-means as the prime mover in their algorithms. However, when an application of fuzzy c-partition has sophisticated constraints, the necessity of analytical solutions in a single iteration step becomes a fatal issue of the existing algorithms. The largest advantage of FBACN is that it does not need analytical solutions. For the problems on which some prior information is known, we bring a combination of part crisp and part fuzzy clustering in the third optimization problem.     

Artificial wavelet neural network and its application in neuro-fuzzy models

In the proposed work, two types of artificial neural networks are proposed by using well-known advantages and valuable features of wavelets and sigmoidal activation functions. Two neurons are derived by adding and multiplying the outputs of the wavelet and the sigmoidal activation functions. These neurons in a feed-forward single hidden layer network result summation wavelet neural network (SWNN) and multiplication wavelet neural network (MWNN). An algorithm is introduced for structure determination of the proposed networks. Approximation properties of SWNN and MWNN have been evaluated with different wavelet functions. The above networks in the consequent part of the neuro-fuzzy model result summation wavelet neuro-fuzzy (SWNF) and multiplication wavelet neuro-fuzzy (MWNF) models. Different types of wavelet function are tested with the proposed networks and fuzzy models on four different dynamical examples. Convergence of the learning process is also guaranteed by adaptive learning rate and performing stability analysis using Lyapunov function.     

Comparison of neofuzzy and rough neural networks

Conventional neural network architectures generally lack semantics. Both rough and neofuzzy neurons introduce semantic structures in the conventional neural network models. Rough neurons make it possible to process data points with a range of values instead of a single precise value. Neofuzzy neurons make it possible to convert crisp values into fuzzy values. This paper compares rough and neofuzzy neural networks. Rough and neofuzzy neurons are demonstrated to be complementary to each other. It is shown that the introduction of rough and fuzzy semantic structures in neural networks can increase the accuracy of predictions.     

Kernel based nonlinear fuzzy regression model

Recent years have seen a surge of interest in extending statistical regression to fuzzy data. Most of the recent fuzzy regression models have undesirable performance when functional relationships are nonlinear. In this study, we propose a novel version of fuzzy regression model, called kernel based nonlinear fuzzy regression model, which deals with crisp inputs and fuzzy output, by introducing the strategy of kernel into fuzzy regression. The kernel based nonlinear fuzzy regression model is identified using fuzzy Expectation Maximization (EM) algorithm based maximum likelihood estimation strategy. Some experiments are designed to show its performance. The experimental results suggest that the proposed model is capable of dealing with the nonlinearity and has high prediction accuracy. Finally, the proposed model is used to monitor unmeasured parameter level of coal powder filling in ball mill in power plant. Driven by running data and expertise, a strategy is first proposed to construct fuzzy outputs, reflecting the possible values taken by the unmeasured parameter. With the engineering application, we then demonstrate the powerful performance of our model.     

脉冲GTAW熔池动态过程模糊神经网络建模与控制

展示了模糊推理与神经网络结合在脉冲GTAW熔池动态过程智能控制中的应用研究 结果.建立了脉冲GTAW平板对接动态过程特征:正反面熔池的最大宽度、长度与面积等参数 的神经网络模型,基于实验数据采用模糊辨识方法提取焊接过程的模糊控制规则,进而设计了 具有自学习适应能力的模糊神经网络控制器.建立了脉冲GTAW熔池动态过程智能控制系统, 焊接实验验证了所设计的模糊神经网络控制器具有智能控制效果.     

Rotation, scale and translation invariant handwritten Devanagari numeral character recognition using general fuzzy neural network

In this paper a general fuzzy hyperline segment neural network is proposed [P.M. Patil, Pattern classification and clustering using fuzzy neural networks, Ph.D. Thesis, SRTMU, Nanded, India, January 2003]. It combines supervised and unsupervised learning in a single algorithm so that it can be used for pure classification, pure clustering and hybrid classification/clustering. The method is applied to handwritten Devanagari numeral character recognition and also to the Fisher Iris database. High recognition rates are achieved with less training and recall time per pattern. The algorithm is rotation, scale and translation invariant. The recognition rate with ring data features is found to be 99.5%.     

On the optimal design of fuzzy neural networks with robust learningfor function approximation

A novel robust learning algorithm for optimizing fuzzy neural networks is proposed to address two important issues: how to reduce the outlier effects and how to optimize fuzzy neural networks, in the function approximation. This algorithm is able to reduce the outlier effects by cooperating with a conventional robust approach, and then to optimize fuzzy neural networks by determining the optimal learning rates which can minimize the next-step mean error at each iteration of our algorithm.