Self-adaptive Training

2000년 도입 · 논문 4편에서 사용

Self-adaptive Training is a training algorithm that dynamically corrects problematic training labels by model predictions to improve generalization of deep learning for potentially corrupted training data. Accumulated predictions are used to augment the training dynamics. The use of an exponential-moving-average scheme alleviates the instability issue of model predictions, smooths out the training target during the training process and enables the algorithm to completely change the training labels if necessary.

출처: Self-Adaptive Training: beyond Empirical Risk Minimization

소개 논문: Self-Adaptive Training: beyond Empirical Risk Minimization