Adaptive Meta-Loss Networks: Learning Task-Agnostic Loss Functions via Evolutionary Optimization
Abstract
Designing appropriate loss functions is critical to the success of supervised learning models. However, most conventional losses are fixed and manually designed, making them suboptimal for diverse and dynamic learning scenari... | Find, read and cite all the research you need on Tech Science Press
Fields of Study & Subjects
Machine Learning and Data Classification
Domain Adaptation and Few-Shot Learning
Evolutionary Algorithms and Applications
Publication details
- Journal / source
- Computers, materials & continua/Computers, materials & continua (Print)
- Volume
- 87
- Issue
- 2
- Pages
- 1–10
- Publication date
- 1 January 2026
- Language
- EN