Interval Type-2 TSK Fuzzy Logic Systems Using Hybrid Learning Algorithm

Mendez, Gerardo M.; Castillo, Oscar

doi:10.1109/fuzzy.2005.1452398

Cited by 42 publications

(25 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [9], all thew i are used as one combination and all thew i are used as another combination. The approach used by Mendez and Juarez [5] is based on the KM algorithms [16]. It will be explained later that the output of layer 5 …”

Section: B It2 Anfismentioning

confidence: 99%

“…The approach used by Mendez and Juarez [5] is based on the KM algorithms [16]. It will be explained later that the output of layer 5 …”

Section: B It2 Anfismentioning

confidence: 99%

“…a) Layer 0: Similar to T1 ANFIS, every node i in this layer is a fuzzifier. However, the fuzzification method can be singleton [5], T1 non-singleton [7,12], as well as IT2 nonsingleton [11,15] …”

Section: B It2 Anfismentioning

confidence: 99%

“…It has been proposed that least-squares based methods cannot be applied to a T2 fuzzy logic system (FLS) Mendel [10], since the Fuzzy Basis Function expansion for a T2 TSK FLS, which is the starting point for the LSE method, cannot be obtained without knowing the consequent parameters in advance. This issue was also concluded in [5] and addressed by giving initialised consequent parameters. In their study, it was proposed that convergence of the hybrid learning algorithms based on the recursive least-squares and the back-propagation (BP) methods can be obtained in practice.…”

Section: Introductionmentioning

confidence: 99%

“…For example, early studies on T2 ANFIS can be found in [2,3], who reported an approach that uses an adaptive network to learn a T2 fuzzy system based on linguistic inputs and numeric output. Other examples for research on T2 ANFIS, based on crisp inputs, can be found in [4,5,6,7,8,9]. It has been proposed that least-squares based methods cannot be applied to a T2 fuzzy logic system (FLS) Mendel [10], since the Fuzzy Basis Function expansion for a T2 TSK FLS, which is the starting point for the LSE method, cannot be obtained without knowing the consequent parameters in advance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An extended ANFIS architecture and its learning properties for type-1 and interval type-2 models

Chen

John

Twycross

et al. 2016

2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

A note on versions:The version presented here may differ from the published version or from the version of record. If you wish to cite this item you are advised to consult the publisher's version. Please see the repository url above for details on accessing the published version and note that access may require a subscription. Abstract-In this paper, an extended ANFIS architecture is proposed. By incorporating an extra layer for the fuzzification process, the extended architecture is able to fit both type-1 and interval type-2 models. The learning properties of the proposed architecture based on the least-squares estimate method are studied on selected type-1 and interval type-2 ANFIS models. We show that the least-squares estimate method in general behaves differently for interval type-2 ANFIS models compared to type-1 ANFIS models, producing larger errors for interval type-2 ANFIS.

show abstract