This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
Accepted at the 
 research sprint on 
February 16, 2023

Physics Guided Deep Learning Interpretation

Nowadays, machine learning and, specifically, deep learning are being utilized in various fields. A notable area of research that is influenced considerably is physics models and computations. Laboratory experiments take days and months to obtain results, and physics models and computations take days in supercomputers. On the other hand, a deep learning model can predict a physical parameter in no time. However, this field is extremely regularized and sensitive; a simple mistake in a physical parameter in fields, including drug discovery, can result in millions of death. In this regard, although there are many fast and super accurate deep learning models in physics problems, none have yet been used widely in the biochemistry industry due to the lack of interpretation and safety measures.

Ali Risheh, Mohammad Rasouli
4th place
3rd place
2nd place
1st place
 by peer review