Open nazaretl opened 2 years ago
Thanks for your interest.
Regarding question 1, what type of tabular data? Recently I am trying some protein sequence data, and I will release it soon.
Regarding question 2, theorectially it is feasible. Just simply detect where predefined labels do not match a model's confident predictions when training is finished.
Hi, thanks for sharing your implementation. I have two questions about it:
Thanks!