yaringal / multi-task-learning-example

A multi-task learning example for the paper https://arxiv.org/abs/1705.07115
MIT License
843 stars 207 forks source link

Question about the loss #13

Open caishiqing opened 3 years ago

caishiqing commented 3 years ago

As described in this paper, the noise(sigma) increases, the respected L(W) decreases. But if we understand sigma as uncertainty of y, maybe it's better for L to be increase with uncertainty, because it means y is harder to learn, so it needs more attention to learn?