Reproducing scientific papers¶

Given:
1. A link to a scientific paper.
2. A link to a repository with the sourcecode for the paper.

Requirements:
1. Report should have your own result on test or validation set.
2. The results should be compared with the paper's one.
3. A slide should contain your experience summary, including you positive feedback, highlighting problems of reproducing, discrepancy reason if present.

Actions:
[0. Find the source codes for the paper.]
1. Run training on a given ML-pipeline if you have enough resources. If no, find available models. If both no, select another paper.
2. Run test on the obtained model.