Difficulty-weighted learning: A novel curriculum-like approach based on difficult examples for neural network training

摘要

Curriculum learning, in which training examples gradually proceed from easy to difficulty, has been applied to various tasks and demonstrated better performance than other machine learning approaches. However, identifying the difficulty level in advance often requires domain knowledge and is a time-consuming process. We dynamically decide the difficulty of examples based on outputs from neural networks during training and propose a loss function to promote training with difficult examples. Experimental results verify that the proposed method improves the generalization ability across several datasets. (C) 2019 Elsevier Ltd. All rights reserved.