Hybrid GPR-DNN Enhanced NSGA-II
Abstract
It constructs a deep learning optimization framework based on Gaussian Process Regression (GPR)-enhanced data augmentation. This approach leverages the Bayesian inference capabilities of GPR to interpolate between sparse samples, thereby enabling the neural network to capture complex physical features that conventional methods might miss.
Fields of Study & Subjects
Advanced Multi-Objective Optimization Algorithms
Metaheuristic Optimization Algorithms Research
Gaussian Processes and Bayesian Inference
Publication details
- Journal / source
- Mendeley Data
- Publication date
- 19 January 2026
- Document type
- Dataset