A fast genetic method for inducting descriptive fuzzy models

Sánchez, Luciano; Otero, José

doi:10.1016/s0165-0114(03)00112-x

Cited by 13 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method is accurate and has been shown to be as fast as some ad-hoc learning methods (Sánchez and Otero 2004). On the other side, when the datasets are imprecise the backfitting results may not be appropriate, as we explain in the next section.…”

Section: Backfitting In Crisp Datasetsmentioning

confidence: 99%

“…The fuzzy rule learning algorithms in Sánchez et al (2006) are: Wang and Mendel (1992) with importance degrees 'maximum', 'mean' and 'product of maximum and mean' (WM1, WM2 and WM3, respectively) the same three versions of Cordón and Herrera's method (Cordón and Herrera 2000) (CH1, CH2, CH3). Nozaki, Ishibuchi and Tanaka's fuzzy rule learning (Nozaki et al 1997) (NIT), TSK rules (Takagi and Sugeno 1985) optimized with Weighted Least Squares and Genetic Backfitting (Sánchez and Otero 2004), and MOSA-based backfitting (Sánchez and Villar 2008;Sánchez et al 2006) (BMO). The same reference includes Linear Regression (LIN), Quadratic Regression (QUA) and a Conjugate-Gradient trained Multilayer Perceptron (NEU).…”

Section: Influence Of the Stochastic Noisementioning

confidence: 99%

“…According to Herrera (2008), there are four genetic techniques for learning KB components: Pittsburgh, Michigan, Iterative Rule Learning (IRL) and Genetic Cooperative-Competitive Learning (GCCL). In previous works (Sánchez et al 2006), we have extended our own implementations of backfitting and boosting, that can be considered part of the IRL approach, to fuzzy data (del Jesus et al 2004;Sánchez and Otero 2004). In this paper, we will do the same with an algorithm of the GCCL type.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Obtaining linguistic fuzzy rule-based regression models from imprecise data with multiobjective genetic algorithms

2008

Self Cite

View full text Add to dashboard Cite

Backfitting of fuzzy rules is an Iterative RuleLearning technique for obtaining the knowledge base of a fuzzy rule-based system in regression problems. It consists in fitting one fuzzy rule to the data, and replacing the whole training set by the residual of the approximation. The obtained rule is added to the knowledge base, and the process is repeated until the residual is zero, or near zero. Such a design has been extended to imprecise data for which the observation error is small. Nevertheless, when this error is moderate or high, the learning can stop early. In this kind of algorithms, the specificity of the residual might decrease when a new rule is added. There may happen that the residual grows so wide that it covers the value zero for all points (thus the algorithm stops), but we have not yet extracted all the information available in the dataset. Focusing on this problem, this paper is about datasets with medium to high discrepancies between the observed and the actual values of the variables, such as those containing missing values and coarsely discretized data. We will show that the quality of the iterative learning degrades in this kind of problems, because it does not make full use of all the available information. As an alternative to sequentially obtaining rules, we propose a new multiobjective Genetic Cooperative Competitive Learning (GCCL) algorithm. In our approach, each individual in the population codifies one rule, which competes in the population in terms of maximum coverage and fitting, while the individuals in the population cooperate to form the knowledge base.

show abstract

Section: Backfitting In Crisp Datasetsmentioning

confidence: 99%

Section: Influence Of the Stochastic Noisementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Obtaining linguistic fuzzy rule-based regression models from imprecise data with multiobjective genetic algorithms

2008

Self Cite

View full text Add to dashboard Cite

show abstract

“…In other publications, 4,5 following the work of Friedman et al, 6 Adaboost is regarded as a forward stepwise estimation of the statistical parameters defining a logit transform of a Generalized Additive Model, and this property is used to extend this last estimation to learn fuzzy models in regression problems. A similar statistical interpretation was used later to improve the fuzzy Adaboost algorithm, again in classification problems.…”

Section: Introductionmentioning

confidence: 99%

Boosting fuzzy rules in classification problems under single-winner inference

Sánchez

Otero

2007

Int. J. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

In previous studies, we have shown that an Adaboost-based fitness can be successfully combined with a Genetic Algorithm to iteratively learn fuzzy rules from examples in classification problems. Unfortunately, some restrictive constraints in the implementation of the logical connectives and the inference method were assumed. Alas, the knowledge bases Adaboost produces are only compatible with an inference based on the maximum sum of votes scheme, and they can only use the t-norm product to model the "and" operator. This design is not optimal in terms of linguistic interpretability. Using the sum to aggregate votes allows many rules to be combined, when the class of an example is being decided. Because it can be difficult to isolate the contribution of individual rules to the knowledge base, fuzzy rules produced by Adaboost may be difficult to understand linguistically. In this point of view, single-winner inference would be a better choice, but it implies dropping some nontrivial hypotheses. In this work we introduce our first results in the search for a boosting-based genetic method able to learn weighted fuzzy rules that are compatible with this last inference method.

show abstract

“…Neuro-fuzzy systems are one of the most successful and visible directions of the efforts [2]. A different approach to hybridization leads to evolutionary fuzzy systems (EFSs) [1,[3][4][5][6]. EFSs are basically fuzzy systems augmented by learning processes based on evolutionary algorithms, such as the genetic algorithm (GA), evolutionary programming (EP), evolutionary strategies (ES), particle swarm optimization (PSO) [7], and any hybridization form of the above evolutionary algorithms.…”

Section: Introductionmentioning

confidence: 99%

Adaptive extended fuzzy basis function network

Zhu

Cao

2006

Neural Comput & Applic

View full text Add to dashboard Cite

The structure of the extended fuzzy basis function network (EFBFN) is firstly proposed, and the least squares (LS) method is used to design it by fixing the widths of the hidden units in EFBFN. Then, to enhance the performance of the obtained EFBFN ulteriorly, a novel evolutionary algorithm based on LS and the hybrid of evolutionary programming and particle swarm optimization (LS-EPPSO) is proposed, in which we use EPPSO to tune the parameters of the premise part in EFBFN, and the LS algorithm to decide the consequent parameters in it simultaneously. The enhanced EFBFN whose parameters are refined automatically using LS-EPPSO is thus called adaptive EFBFN. In the simulation part, the proposed method to construct AEFBFN is employed to model a three input nonlinear function and to predict a chaotic time series. Comparisons with some typical fuzzy modeling methods and artificial neural networks are presented and discussed.

show abstract

A fast genetic method for inducting descriptive fuzzy models

Cited by 13 publications

References 16 publications

Obtaining linguistic fuzzy rule-based regression models from imprecise data with multiobjective genetic algorithms

Obtaining linguistic fuzzy rule-based regression models from imprecise data with multiobjective genetic algorithms

Boosting fuzzy rules in classification problems under single-winner inference

Adaptive extended fuzzy basis function network

Contact Info

Product

Resources

About