## Neuro-Fuzzy Systems for Function Approximation (1999)

Venue: | Fuzzy Sets and Systems |

Citations: | 34 - 1 self |

### BibTeX

@ARTICLE{Nauck99neuro-fuzzysystems,

author = {Detlef Nauck and Rudolf Kruse},

title = {Neuro-Fuzzy Systems for Function Approximation},

journal = {Fuzzy Sets and Systems},

year = {1999},

volume = {101},

pages = {261--271}

}

### Years of Citing Articles

### OpenURL

### Abstract

We propose a neuro--fuzzy architecture for function approximation based on supervised learning. The learning algorithm is able to determine the structure and the parameters of a fuzzy system. The approach is an extension to our already published NEFCON and NEFCLASS models which are used for control or classification purposes. The proposed extended model, which we call NEFPROX, is more general and can be used for any application based on function approximation. Keywords: neuro--fuzzy system, function approximation, structure learning, parameter learning 1 Introduction Certain fuzzy systems are universal function approximators [1, 4]. In order to identify a suitable fuzzy system for a given problem, membership functions (parameters) and a rule base (structure) must be specified. This can be done by prior knowledge, by learning, or by a combination of both. If a learning algorithm is applied that uses local information and causes local modifications in a fuzzy system, this approach is us...

### Citations

3629 |
Neural Networks: A Comprehensive Foundation (2 nd ed
- Haykin
- 1999
(Show Context)
Citation Context ... crisp classification tasks. We call this approach NEFPROX (NEuro Fuzzy function apPROXimator). 2 Architecture Function approximation based on local learning strategies is a domain of neural networks =-=[2]-=- and neuro--fuzzy systems [7]. Neuro--fuzzy systems have the advantage that they can use prior knowledge, whereas neural networks have to learn from scratch. In addition neural networks are black boxe... |

434 | ANFIS: adaptive-network-based fuzzy inference system
- Jang
- 1993
(Show Context)
Citation Context ...arn from scratch. In addition neural networks are black boxes, and they can usually not be interpreted in form of rules. A well known neuro--fuzzy system for function approximation is the ANFIS model =-=[3]-=-. However there is no algorithm given for structure learning, and it is used to implement Sugeno models with differentiable functions (e.g. product as t--norm). We propose a more general approach that... |

128 |
Fuzzy systems as universal approximators
- Kosko
- 1994
(Show Context)
Citation Context ...ased on function approximation. Keywords: neuro--fuzzy system, function approximation, structure learning, parameter learning 1 Introduction Certain fuzzy systems are universal function approximators =-=[1, 4]-=-. In order to identify a suitable fuzzy system for a given problem, membership functions (parameters) and a rule base (structure) must be specified. This can be done by prior knowledge, by learning, o... |

46 | NEFCLASS - A Neuro-Fuzzy Approach for the Classification of Data
- Nauck, Kruse
- 1995
(Show Context)
Citation Context ...al information and causes local modifications in a fuzzy system, this approach is usually called neuro--fuzzy system [7]. We have already presented two neuro--fuzzy approaches NEFCON [5] and NEFCLASS =-=[6, 8]-=-. The first one is used for control applications, and is trained by reinforcement learning based on a fuzzy error measure. The second one is used for classification of data, and is based on supervised... |

31 |
Sugeno type controllers are universal controllers
- Buckley
- 1993
(Show Context)
Citation Context ...ased on function approximation. Keywords: neuro--fuzzy system, function approximation, structure learning, parameter learning 1 Introduction Certain fuzzy systems are universal function approximators =-=[1, 4]-=-. In order to identify a suitable fuzzy system for a given problem, membership functions (parameters) and a rule base (structure) must be specified. This can be done by prior knowledge, by learning, o... |

19 |
Designing Neuro-Fuzzy Systems Through Back-Propagation, in: Pedrycz W. (Ed.), Fuzzy Modeling: Paradigms and Practice
- Nauck, Kruse
- 1996
(Show Context)
Citation Context ...ning, or by a combination of both. If a learning algorithm is applied that uses local information and causes local modifications in a fuzzy system, this approach is usually called neuro--fuzzy system =-=[7]-=-. We have already presented two neuro--fuzzy approaches NEFCON [5] and NEFCLASS [6, 8]. The first one is used for control applications, and is trained by reinforcement learning based on a fuzzy error ... |

14 | Generating classification rules with the neuro-fuzzy system
- Nauck, Nauck, et al.
- 1996
(Show Context)
Citation Context ...al information and causes local modifications in a fuzzy system, this approach is usually called neuro--fuzzy system [7]. We have already presented two neuro--fuzzy approaches NEFCON [5] and NEFCLASS =-=[6, 8]-=-. The first one is used for control applications, and is trained by reinforcement learning based on a fuzzy error measure. The second one is used for classification of data, and is based on supervised... |

11 |
Building Neural Fuzzy Controllers with NEFCON--I
- Nauck
- 1994
(Show Context)
Citation Context ...ied that uses local information and causes local modifications in a fuzzy system, this approach is usually called neuro--fuzzy system [7]. We have already presented two neuro--fuzzy approaches NEFCON =-=[5]-=- and NEFCLASS [6, 8]. The first one is used for control applications, and is trained by reinforcement learning based on a fuzzy error measure. The second one is used for classification of data, and is... |