IC-FNN: A Novel Fuzzy Neural Network With Interpretable, Intuitive, and Correlated-Contours Fuzzy Rules for Function Approximation

Ebadzadeh, Mohammad Mehdi; Salimi-Badr, Armin

doi:10.1109/tfuzz.2017.2718497

Cited by 49 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the dimension of the state space is large, or the state space is contiguous, the value function cannot be represented by a table. At this time, it is necessary to represent the value function by means of function approximation [30].…”

Section: Methodsmentioning

confidence: 99%

Research on predicting 2D-HP protein folding using reinforcement learning with full state space

Yang

et al. 2019

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundProtein structure prediction has always been an important issue in bioinformatics. Prediction of the two-dimensional structure of proteins based on the hydrophobic polarity model is a typical non-deterministic polynomial hard problem. Currently reported hydrophobic polarity model optimization methods, greedy method, brute-force method, and genetic algorithm usually cannot converge robustly to the lowest energy conformations. Reinforcement learning with the advantages of continuous Markov optimal decision-making and maximizing global cumulative return is especially suitable for solving global optimization problems of biological sequences.ResultsIn this study, we proposed a novel hydrophobic polarity model optimization method derived from reinforcement learning which structured the full state space, and designed an energy-based reward function and a rigid overlap detection rule. To validate the performance, sixteen sequences were selected from the classical data set. The results indicated that reinforcement learning with full states successfully converged to the lowest energy conformations against all sequences, while the reinforcement learning with partial states folded 50% sequences to the lowest energy conformations. Reinforcement learning with full states hits the lowest energy on an average 5 times, which is 40 and 100% higher than the three and zero hit by the greedy algorithm and reinforcement learning with partial states respectively in the last 100 episodes.ConclusionsOur results indicate that reinforcement learning with full states is a powerful method for predicting two-dimensional hydrophobic-polarity protein structure. It has obvious competitive advantages compared with greedy algorithm and reinforcement learning with partial states.

show abstract

Section: Methodsmentioning

confidence: 99%

Research on predicting 2D-HP protein folding using reinforcement learning with full state space

Yang

et al. 2019

BMC Bioinformatics

View full text Add to dashboard Cite

show abstract

“…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%

“…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%

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

“…Deep learning contains many different types for different problems, which are DNN, recurrent neural network (RNN), convolutional neural network (CNN), and deep autoencoder (DA). [26][27][28]…”

Section: Deep Learningmentioning

confidence: 99%

Deep Petri nets of unsupervised and supervised learning

Lin

Hsieh

Yang

et al. 2020

Measurement and Control

View full text Add to dashboard Cite

Artificial intelligence is one of the hottest research topics in computer science. In general, when it comes to the needs to perform deep learning, the most intuitive and unique implementation method is to use neural network. But there are two shortcomings in neural network. First, it is not easy to be understood. When encountering the needs for implementation, it often requires a lot of relevant research efforts to implement the neural network. Second, the structure is complex. When constructing a perfect learning structure, in order to achieve the fully defined connection between nodes, the overall structure becomes complicated. It is hard for developers to track the parameter changes inside. Therefore, the goal of this article is to provide a more streamlined method so as to perform deep learning. A modified high-level fuzzy Petri net, called deep Petri net, is used to perform deep learning, in an attempt to propose a simple and easy structure and to track parameter changes, with faster speed than the deep neural network. The experimental results have shown that the deep Petri net performs better than the deep neural network.

show abstract

IC-FNN: A Novel Fuzzy Neural Network With Interpretable, Intuitive, and Correlated-Contours Fuzzy Rules for Function Approximation

Cited by 49 publications

References 54 publications

Research on predicting 2D-HP protein folding using reinforcement learning with full state space

Research on predicting 2D-HP protein folding using reinforcement learning with full state space

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

Deep Petri nets of unsupervised and supervised learning

Contact Info

Product

Resources

About