problem about reproduction

Open Tirthikas opened this issue 5 years ago • 1 comments

When I try to reproduce the experiments results in the paper, I cannot get a approximate result as in the paper. And I want to know why you choose this neural network structure, and I think you might have a misunderstanding on multi-task machine learning...

Dec 18 '20 12:12 Tirthikas

When I try to reproduce the experiments results in the paper, I cannot get an approximate result as in the paper.

Can you describe your problem with the reproduction?

I want to know why you choose this neural network structure

Please see our paper: arxiv.org/abs/2005.12392

I think you might have a misunderstanding on multi-task machine learning

Can you expand on why you think so?

Dec 18 '20 14:12 rahlk