RGBChem: Image-Like Representation of Chemical Compounds for Property Prediction
Sign Up to like & getrecommendations! Published in 2025 at "Journal of Chemical Theory and Computation"
DOI: 10.1021/acs.jctc.5c00291
Abstract: In this work, we introduce RGBChem, a novel approach for converting chemical compounds into image representations, which are subsequently used to train a convolutional neural network (CNN) to predict the HOMO–LUMO gap for compounds from… read more here.
Keywords: image like; rgbchem; chemical compounds; rgbchem image ... See more keywords
Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data
Sign Up to like & getrecommendations! Published in 2021 at "Nature Communications"
DOI: 10.1038/s41467-021-23952-w
Abstract: Image-like data from quantum systems promises to offer greater insight into the physics of correlated quantum matter. However, the traditional framework of condensed matter physics lacks principled approaches for analyzing such data. Machine learning models… read more here.
Keywords: image; correlator convolutional; image like; physics ... See more keywords