IT2CFNN: An interval type-2 correlation-aware fuzzy neural network to construct non-separable fuzzy rules with uncertain and adaptive shapes for nonlinear function approximation

Salimi-Badr, Armin

doi:10.1016/j.asoc.2021.108258

Cited by 14 publications

(10 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some usual approaches to solve the structure identification problem including using different clustering methods [45,25,26,50], online clustering methods [62,63,37,49,51,12,53], and uniformly partitioning [35,27]. The proposed structure is a control unit that should cover the whole input space properly.…”

Section: Learning Methodsmentioning

confidence: 99%

“…An usual approach to learn consequent parts' parameters of a fuzzy neural network is to minimize the error between the desired and actual output values using local search algorithms including Gradient Descent (GD), Levenberg-Marquardt A novel evolutionary-based neuro-fuzzy task scheduling approach to jointly optimize the main design challenges of heterogeneous MPSoCs (LM), or Linear Least Square Error (LLS) methods [38,25,26,50,52]. Here, the desired output values (the "labels" in the supervised learning) are not available.…”

Section: Learning Methodsmentioning

confidence: 99%

“…Fuzzy Inference Systems (FISs) are rule based decision making systems including a set of "IF-THEN" linguistic rules [50,52,40,23,26,53,25,51,35,49,20,15,13]. One of the main advantage of these systems is their interpretability.…”

Section: Fuzzy Inference Systemsmentioning

confidence: 99%

“…To add learning ability to FISs, Fuzzy Neural Networks (FNN) are proposed that have the interpretability advantage of FIS along with adaptive structure of Neural Networks [40,23,35,50].…”

Section: Fuzzy Inference Systemsmentioning

confidence: 99%

“…Since these systems are built upon fuzzy logic, they can model uncertainty mathematically in the input variables considering them as linguistic variables [68,47,23]. Therefore, they are successfully applied to applications encountering uncertainty like control, function approximation, resource allocation, and time-series prediction [30,50,52,40,26,53,25,51,35,49,20,15,13]. Considering the online scheduling as a control application that assigns different cores the ready task based on the received uncertain sensor measurements as the feedback, it is expected to successfully apply a fuzzy inference system to this problem.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A novel evolutionary-based neuro-fuzzy task scheduling approach to jointly optimize the main design challenges of heterogeneous MPSoCs

Abdi¹,

Salimi-Badr²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, an online task scheduling and mapping method based on a fuzzy neural network (FNN) learned by an evolutionary multi-objective algorithm (NSGA-II) to jointly optimize the main design challenges of heterogeneous MPSoCs is proposed. In this approach, first, the FNN parameters are trained using an NSGA-II-based optimization engine by considering the main design challenges of MPSoCs including temperature, power consumption, failure rate, and execution time on a training dataset consisting of different application graphs of various sizes. Next, the trained FNN is employed as an online task scheduler to jointly optimize the main design challenges in heterogeneous MPSoCs. Due to the uncertainty in sensor measurements and the difference between computational models and reality, applying the fuzzy neural network is advantageous in online scheduling procedures. The performance of the method is compared with some previous heuristic, meta-heuristic, and rule-based approaches in several experiments. Based on these experiments our proposed method outperforms the related studies in optimizing all design criteria. Its improvement over related heuristic and meta-heuristic approaches are estimated 10.58% in temperature, 9.22% in power consumption, 39.14% in failure rate, and 12.06% in execution time, averagely. Moreover, considering the interpretable nature of the FNN, the frequently fired extracted fuzzy rules of the proposed approach are demonstrated.

show abstract

Section: Learning Methodsmentioning

confidence: 99%

Section: Learning Methodsmentioning

confidence: 99%

Section: Fuzzy Inference Systemsmentioning

confidence: 99%

“…To add learning ability to FISs, Fuzzy Neural Networks (FNN) are proposed that have the interpretability advantage of FIS along with adaptive structure of Neural Networks [40,23,35,50].…”

Section: Fuzzy Inference Systemsmentioning

confidence: 99%