2017
DOI: 10.1109/tcyb.2016.2638861
|View full text |Cite
|
Sign up to set email alerts
|

Efficient Approach for RLS Type Learning in TSK Neural Fuzzy Systems

Abstract: This paper presents an efficient approach for the use of recursive least square (RLS) learning algorithm in Takagi-Sugeno-Kang neural fuzzy systems. In the use of RLS, reduced covariance matrix, of which the off-diagonal blocks defining the correlation between rules are set to zeros, may be employed to reduce computational burden. However, as reported in the literature, the performance of such an approach is slightly worse than that of using the full covariance matrix. In this paper, we proposed a so-called en… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
14
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 28 publications
(14 citation statements)
references
References 46 publications
0
14
0
Order By: Relevance
“…We note that other supervised-learning methods, e.g. multi-relational classification models [78], deep fuzzy models [50,77], and deep residual models [27,45] may improve the prediction accuracy of the reward oracles and affect the performance of the algorithm. However, these implementations are expected to be explored further in the future works.…”
Section: B Experiments Settingsmentioning
confidence: 99%
“…We note that other supervised-learning methods, e.g. multi-relational classification models [78], deep fuzzy models [50,77], and deep residual models [27,45] may improve the prediction accuracy of the reward oracles and affect the performance of the algorithm. However, these implementations are expected to be explored further in the future works.…”
Section: B Experiments Settingsmentioning
confidence: 99%
“…NFINs can be divided into two types: Mamdani-type NFINs (M-NFINs) (4,5) and Takagi-Sugeno-Kang (TSK)-type NFINs (T-NFINs). (6)(7)(8) The fuzzy reasoning in an M-NFIN involves the minimum fuzzy implication rule. However, in a T-NFIN, the consequence of each fuzzy rule is a linear function including a combination of input variables.…”
Section: Introductionmentioning
confidence: 99%
“…However, in a T-NFIN, the consequence of each fuzzy rule is a linear function including a combination of input variables. Many studies (7,8) have shown that a T-NFIN achieves superior performance to an M-NFIN in terms of accuracy and network size. In general, the function involving a combination of input variables in a T-NFIN is linear.…”
Section: Introductionmentioning
confidence: 99%
“…In this context, the fast and accurate control scheme in complex situations is highly desirable for a USV which pursues high‐accuracy mission efficiency. Recently, some approaches to attenuate complex unknowns have turned to fuzzy logic system, 32‐34 neural networks, 35‐40 and reinforcement learning 41 . However, the aforementioned approximation‐based approaches can only achieve asymptotic/exponential stability with bounded tracking residuals.…”
Section: Introductionmentioning
confidence: 99%