Results 1  10
of
135
AdaptiveNetworkBased Fuzzy Inference System
 IEEE Transactions on Systems, Man, and Cybernetics
, 1993
"... ..."
Functional Equivalence between Radial Basis Function Networks and Fuzzy Inference Systems
, 1993
"... This short article shows that under some minor restrictions, the functional behavior of radial basis function networks and fuzzy inference systems are actually equivalent. This functional equivalence implies that advances in each literature, such as new learning rules or analysis on representational ..."
Abstract

Cited by 133 (4 self)
 Add to MetaCart
This short article shows that under some minor restrictions, the functional behavior of radial basis function networks and fuzzy inference systems are actually equivalent. This functional equivalence implies that advances in each literature, such as new learning rules or analysis on representational power, etc., can be applied to both models directly. It is of interest to observe that twomodels stemming from different origins turn out to be functional equivalent.
Designing fuzzy inference systems from data: an interpretabilityoriented review
 IEEE Trans. Fuzzy Systems
"... Abstract—Fuzzy inference systems (FIS) are widely used for process simulation or control. They can be designed either from expert knowledge or from data. For complex systems, FIS based on expert knowledge only may suffer from a loss of accuracy. This is the main incentive for using fuzzy rules infer ..."
Abstract

Cited by 50 (9 self)
 Add to MetaCart
Abstract—Fuzzy inference systems (FIS) are widely used for process simulation or control. They can be designed either from expert knowledge or from data. For complex systems, FIS based on expert knowledge only may suffer from a loss of accuracy. This is the main incentive for using fuzzy rules inferred from data. Designing a FIS from data can be decomposed into two main phases: automatic rule generation and system optimization. Rule generation leads to a basic system with a given space partitioning and the corresponding set of rules. System optimization can be done at various levels. Variable selection can be an overall selection or it can be managed rule by rule. Rule base optimization aims to select the most useful rules and to optimize rule conclusions. Space partitioning can be improved by adding or removing fuzzy sets and by tuning membership function parameters. Structure optimization is of a major importance: selecting variables, reducing the rule base and optimizing the number of fuzzy sets. Over the years, many methods have become available for designing FIS from data. Their efficiency is usually characterized by a numerical performance index. However, for humancomputer cooperation another criterion is needed: the rule interpretability. An implicit assumption states that fuzzy rules are by nature easy to be interpreted. This could be wrong when dealing with complex multivariable systems or when the generated partitioning is meaningless for experts. This paper analyzes the main methods for automatic rule generation and structure optimization. They are grouped into several families and compared according to the rule interpretability criterion. For this purpose, three conditions for a set of rules to be interpretable are defined. Index Terms—Fuzzy inference systems, fuzzy partitioning, interpretability, rule induction, system optimization. I.
Neural Networks in Designing Fuzzy Systems for Real World Applications”, Fuzz y
 University of Sydney
, 1995
"... AbstractA special multilayer perceptron architecture known as FuNe I is successfully used for generating fuzzy systems for a number of real world applications. The FuNe I trained with supervised learning can be used to extract fuzzy rules from a given representative input/output data set. Furthermo ..."
Abstract

Cited by 47 (8 self)
 Add to MetaCart
AbstractA special multilayer perceptron architecture known as FuNe I is successfully used for generating fuzzy systems for a number of real world applications. The FuNe I trained with supervised learning can be used to extract fuzzy rules from a given representative input/output data set. Furthermore, optimization of the knowledge base is possible including the tuning of membership functions. The new method employed to identify the rule relevant nodes before the rules are extracted makes FuNe I suitable for applications with large number of inputs. Some of the real world applicationsinareas of state identi cation and image classi cation show encouraging results in a shorter development time. Expert knowledge is not compulsory but can be included in the automatically extracted knowledge base. The generated fuzzy system can be implemented in hardware very easily. A exible prototype board is developed with a FPGA chip in order to run applications with up to 128 inputs and 4 outputs in realtime (1.25 million rules per second).
Improving the interpretability of TSK fuzzy models by combining global and local learning
 IEEE Trans. Fuzzy Syst
, 1998
"... Abstract — The fuzzy inference system proposed by Takagi, Sugeno, and Kang, known as the TSK model in fuzzy system literature, provides a powerful tool for modeling complex nonlinear systems. Unlike conventional modeling where a single model is used to describe the global behavior of a system, TSK ..."
Abstract

Cited by 37 (1 self)
 Add to MetaCart
Abstract — The fuzzy inference system proposed by Takagi, Sugeno, and Kang, known as the TSK model in fuzzy system literature, provides a powerful tool for modeling complex nonlinear systems. Unlike conventional modeling where a single model is used to describe the global behavior of a system, TSK modeling is essentially a multimodel approach in which simple submodels (typically linear models) are combined to describe the global behavior of the system. Most existing learning algorithms for identifying the TSK model are based on minimizing the square of the residual between the overall outputs of the real system and the identified model. Although these algorithms can generate a TSK model with good global performance (i.e., the model is capable of approximating the given system with arbitrary accuracy, provided that sufficient rules are used and sufficient training data are available), they cannot guarantee the resulting model to have a good local performance. Often, the submodels in the TSK model may exhibit an erratic local behavior, which is difficult to interpret. Since one of the important motivations of using the TSK model (also other fuzzy models) is to gain insights into the model, it is important to investigate the interpretability issue of the TSK model. In this paper, we propose a new learning algorithm that integrates global learning and local learning in a single algorithmic framework. This algorithm uses the idea of local weighed regression and local approximation in nonparametric statistics, but remains the component of global fitting in the existing learning algorithms. The algorithm is capable of adjusting its parameters based on the user’s preference, generating models with good tradeoff in terms of global fitting and local interpretation. We illustrate the performance of the proposed algorithm using a motorcycle crash modeling example. Index Terms—Fuzzy modeling, fuzzy systems, learning algorithms, TSK model. I.
Combined Genetic Algorithm Optimization and Regularized Orthogonal Least Squares Learning for Radial Basis Function Networks
, 1999
"... The paper presents a twolevel learning method for radial basis function (RBF) networks. A regularized orthogonal least squares (ROLS) algorithm is employed at the lower level to construct RBF networks while the two key learning parameters, the regularization parameter and the RBF width, are optimiz ..."
Abstract

Cited by 29 (8 self)
 Add to MetaCart
The paper presents a twolevel learning method for radial basis function (RBF) networks. A regularized orthogonal least squares (ROLS) algorithm is employed at the lower level to construct RBF networks while the two key learning parameters, the regularization parameter and the RBF width, are optimized using a genetic algorithm (GA) at the upper level. Nonlinear time series modeling and prediction is used as an example to demonstrate the effectiveness of this hierarchical learning approach.
Operating regime based process modeling and identification ph.d thesis
"... the Department of Engineering Cybernetics, who has been of great inspiration and support. Thanks. Moreover, I would like to thank Prof. Petros Ioannou at the UniversityofSouthern California for hosting my six month visit at USC. My interactions with him and his students improved my mathematical prec ..."
Abstract

Cited by 28 (12 self)
 Add to MetaCart
the Department of Engineering Cybernetics, who has been of great inspiration and support. Thanks. Moreover, I would like to thank Prof. Petros Ioannou at the UniversityofSouthern California for hosting my six month visit at USC. My interactions with him and his students improved my mathematical precision and resulted in some adaptive control results that are partially reported in this thesis. Two chapters in this thesis are based on manuscripts that are coauthored with Aage V. S rensen at
The Shape of Fuzzy Sets in Adaptive Function Approximation
, 2001
"... The shape of ifpart fuzzy sets affects how well feedforward fuzzy systems approximate continuous functions. We explore a wide range of candidate ifpart sets and derive supervised learning laws that tune them. Then we test how well the resulting adaptive fuzzy systems approximate a battery of test ..."
Abstract

Cited by 18 (3 self)
 Add to MetaCart
The shape of ifpart fuzzy sets affects how well feedforward fuzzy systems approximate continuous functions. We explore a wide range of candidate ifpart sets and derive supervised learning laws that tune them. Then we test how well the resulting adaptive fuzzy systems approximate a battery of test functions. No one set shape emerges as the best shape. The sinc function often does well and has a tractable learning law. But its undulating sidelobes may have no linguistic meaning. This suggests that the engineering goal of functionapproximation accuracy may sometimes have to outweigh the linguistic or philosophical interpretations of fuzzy sets that have accompanied their use in expert systems. We divide the ifpart sets into two large classes. The first class consists ofdimensional joint sets that factor into scalar sets as found in almost all published fuzzy systems. These sets ignore the correlations among vector components of input vectors. Fuzzy systems that use factorable ifpart sets suffer in general from exponential rule explosion in high dimensions when they blindly approximate functions without knowledge of the functions. The factorable fuzzy sets themselves also suffer from what we call the second curse of dimensionality: The fuzzy sets tend to become binary spikes in high dimension. The second class of ifpart sets consists of the more general but less commondimensional joint sets that do not factor into scalar fuzzy sets. We present a method for constructing such unfactorable joint sets from scalar distance measures. Fuzzy systems that use unfactorable ifpart sets need not suffer from exponential rule explosion but their increased complexity may lead to intractable learning laws and inscrutable ifthen rules. We prove that some of these unfactorable join...
Fuzzy rulebased networks for control
 IEEE Trans. Fuzzy Syst
, 1994
"... Abstract  We present a method for the learning of fuzzy logic membership functions and rules to approximate a numerical function from a set of examples of the function's independent variables and the resulting function value. This method uses a threestep approach to building a complete functi ..."
Abstract

Cited by 17 (0 self)
 Add to MetaCart
Abstract  We present a method for the learning of fuzzy logic membership functions and rules to approximate a numerical function from a set of examples of the function's independent variables and the resulting function value. This method uses a threestep approach to building a complete function approximation system: rst, learning the membership functions and creating a cellbased rule representation; second, simplifying the cellbased rules using an informationtheoretic approach for induction of rules from discretevalued data; and nally, constructing a computational (neural) network to compute the function value given its independent variables. This function approximation system is demonstrated with a simple control example: learning the truck and trailer backerupper control system. I.
Fuzzy Rule Based Modeling As A Universal Approximation Tool
, 1996
"... INTRODUCTION 1.1. WHY UNIVERSAL APPROXIMATION In some cases, fuzzy rule based model needs tuning. If we have applied some version of fuzzy rule based modeling, and the resulting model is satisfactory, great. But sometimes, the resulting model is not of very high quality: \Gamma we may have misint ..."
Abstract

Cited by 16 (12 self)
 Add to MetaCart
INTRODUCTION 1.1. WHY UNIVERSAL APPROXIMATION In some cases, fuzzy rule based model needs tuning. If we have applied some version of fuzzy rule based modeling, and the resulting model is satisfactory, great. But sometimes, the resulting model is not of very high quality: \Gamma we may have misinterpreted some of the expert's rules; \Gamma we may have missed some of the important rules. So, to improve the quality of the resulting model, we must either: \Gamma reinterpret the existing rules, or \Gamma ask the experts for extra rules. 2 V. KREINOVICH ET AL. Before we start tuning, we want to make sure that tuning will help. In order to make sure that this "tuning" will always help, we must guarantee that by appropriate tuning, we will be able to change the initial (not very successful) model into a successful one. To guarantee that the fuzzy rule based modeling me