2008
DOI: 10.1109/tfuzz.2007.905918
|View full text |Cite
|
Sign up to set email alerts
|

Efficient Hardware/Software Implementation of an Adaptive Neuro-Fuzzy System

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
36
0

Year Published

2008
2008
2019
2019

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 64 publications
(36 citation statements)
references
References 35 publications
0
36
0
Order By: Relevance
“…In addition, the tool generates the object code for developing both on-line and off-line training applications. The tool has been tested extensively by means of several nonlinear functions [31] and it has been used to develop efficient SW solutions, high performance HW solutions, and hybrid HW/SW approaches [32,33,34].…”
Section: A Design Methodology Based On the Pwm-anfis Toolmentioning
confidence: 99%
See 1 more Smart Citation
“…In addition, the tool generates the object code for developing both on-line and off-line training applications. The tool has been tested extensively by means of several nonlinear functions [31] and it has been used to develop efficient SW solutions, high performance HW solutions, and hybrid HW/SW approaches [32,33,34].…”
Section: A Design Methodology Based On the Pwm-anfis Toolmentioning
confidence: 99%
“…12(a) shows an example with four and seven membership functions for two input variables. These restrictions allow considerably reduce the computational cost of the modeling process and to simplify implementation hypothetical Hardware (HW) of the approximate network [35,32,34]. This choice shown in Fig.…”
Section: Pwm-anfismentioning
confidence: 99%
“…The sequential implementations in most of the cases cannot work in real time, but a parallelized structure of the operations could be a solution. There are many related works to the implementations of neuro-fuzzy models, using different techniques [1], [2], [3]. The best platform to realize embedded systems with parallel architectures is the Field Programmable Gate Array (FPGA).…”
Section: Introductionmentioning
confidence: 99%
“…Similar to the back-propagation algorithm for neural networks, a so-called ''Gradient-based Neuro-Fuzzy learning algorithm" (GNF) is commonly used for neuro-fuzzy models [4,9,10,18,22,[26][27][28]33,35,40]. There have been many thorough convergence results for the gradient learning methods for neural networks, but barely any for neuro-fuzzy models.…”
Section: Introductionmentioning
confidence: 99%
“…We are concerned with the gradient method (GNF) for zero-order Takagi-Sugeno inference system [4,6,9,10,19,25,30], which is a special class of neuro-fuzzy models. Our contributions in this paper are to modify a commonly used GNF for a better learning performance, and to provide a rigorous convergence analysis for the modified learning method.…”
Section: Introductionmentioning
confidence: 99%