Michael Moor

Results 3 comments of Michael Moor

I haven't actually tried which works better yet, but I can gladly start a PR adding the meta_lr_final for making the decay working properly (otherwise ppl may believe they are...

Dear Sree, I am very interested in extending the analysis to e-ICU. Apparently, it is not super straightforward to implement Sepsis-3 on eICU which is why in the Nature paper,...

Thank you, will look into this. We used a single 40G A100 for inference (without any optimization for inference), but may work on slightly smaller GPU memory as well (I...