自步学习(Self-Paced Learning)的损失函数
对文章 Self-paced Learning-for Latent Variable Models 中损失函数的由来进行解读
(最好对应着原论文看哦~)
不谈SPL的理论了,别的资料里说的很多~只聊聊损失函数的形式
之后有机会分析下以下三篇
- Self-paced Convolutional Neural Networks
- Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search
- What Objective Does Self-paced Learning Indeed Optimize?