Deciphering Molecular Embeddings with Centered Kernel Alignment
Sign Up to like & getrecommendations! Published in 2024 at "Journal of Chemical Information and Modeling"
DOI: 10.1021/acs.jcim.4c00837
Abstract: Analyzing machine learning models, especially nonlinear ones, poses significant challenges. In this context, centered kernel alignment (CKA) has emerged as a promising model analysis tool that assesses the similarity between two embeddings. CKA’s efficacy depends… read more here.
Keywords: molecular embeddings; centered kernel; deciphering molecular; model analysis ... See more keywords