A5049296658- Neural Networks and Applications
- Advanced Decision-Making Techniques
- Metaheuristic Optimization Algorithms Research
- Fuzzy Logic and Control Systems
- Face and Expression Recognition
- Constraint Satisfaction and Optimization
- Data Mining Algorithms and Applications
- Image and Video Stabilization
- Image Processing and 3D Reconstruction
Universiti Sains Malaysia
2022-2024
Recently, new variants of non-systematic satisfiability logic were proposed to govern Discrete Hopfield Neural Network. This variant logical rule will provide flexibility and enhance the diversity neuron states in However, there is no systematic method control optimize structure satisfiability. Additionally, role negative literals was neglected, reducing expressivity information that holds. study an additional optimization layer Network called phase controls distribution structure. Hence, a...
Real life logical rule is not always satisfiable in nature due to the redundant variable that represents formulation. Thus, intelligence system must be optimally governed ensure can behave according non-satisfiable structure finds practical applications particularly knowledge discovery tasks. In this paper, we a propose non-satisfiability combines two sub-logical rules, namely Maximum 2 Satisfiability and Random Satisfiability, play vital role creating explainable artificial intelligence....
In a binary Artificial Bee Colony, the exploration mechanism occurs in nectar equation where it improvises search space to obtain an optimal solution rapidly. However, there is much uncertainty about which parameter operates well optimizing discrete problems. this study, focus modification of nectars by replacing NAND logic gate ABC called nand-ABC. The proposed model will be integrated into stage generate Weighted Random k Satisfiability for k=1, 2 that takes account higher ratio negative...