Interpretability and structural machine learning versus knowledge-base chemical property prediction

Project detail

Natalia SEGURA ALABART

-


Interpretability and structural machine learning versus knowledge-base chemical property prediction

Predicting molecular properties such as solubility is a key challenge in computational chemistry and materials science. Machine learning offers a promising approach to model these properties efficiently, yet different paradigms exist for representing chemical information.

26-NOV-2025

Graph Neural Networks; Transfer Learning; Model Interpretability; Property Prediction

-


Màster universitari en Enginyeria de la Seguretat Informàtica i Intel·ligència Artificial
Intel·ligència artificial - GEI, MESIIA

Completed

Company
Confidential
English
Service Learning

Assigned student

Name Surname Assignment Date Course
JEAN PHILIPPE LEMOINE ROMERO 01-SEP-2025 2025-2026

Files

File Document Type Description
Memoria_LEMOINEROMERO_JEANPHILIPPE.pdf Memòria

Tribunal

lab231

17-JUN-2026 09:00


Pedro GARCÍA LÓPEZ

Francesc SERRATOSA I CASANELLES

Aïda VALLS MATEU