Time frequency representations and deep convolutional neural networks: a recipe for molecular properties prediction

Par Conseil national de recherches du Canada

DOI	Trouver le DOI : https://doi.org/10.1109/CCECE53047.2021.9569072
Auteur	Rechercher : Tchagang, Alain B.¹; Rechercher : Valdes, Julio J.¹
Affiliation	Conseil national de recherches du Canada. Technologies numériques
Format	Texte, Article
Conférence	2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Sept 12-17, 2021, Held Virtually
Sujet	convolutional neural networks; Coulomb matrix; density functional theory; molecular forward design; time-frequency representations
Résumé	In recent years, Quantum Mechanics (QM) has been combined with Machine Learning (ML) algorithms to speed up the design of molecules, drugs and materials. These paradigms known as QM↔ML have been successful in providing the precision of QM at the speed of ML. In this work, we show that by integrating well-known signal processing (SP) techniques in the QM↔ML pipeline, we obtain a powerful methodology (QM↔SP↔ML) that can be used for representation, visualization and molecular properties predictions. Tested on the benchmark QM9 dataset, the new QM↔SP↔ML framework is able to predict the properties of molecules with a mean absolute error below acceptable chemical accuracy, and yield better or similar results compared to other ML state-of-the-art techniques described in the literature.
Date de publication	2021-10-26
Maison d’édition	IEEE
Dans	2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) (26 octobre 2021) : 1–5.
Langue	anglais
Publications évaluées par des pairs	Oui
Exporter la notice	Exporter en format RIS
Signaler une correction	Signaler une correction (s'ouvre dans un nouvel onglet)
Identificateur de l’enregistrement	1237329f-fe08-4c94-bca6-65079da70938
Enregistrement créé	2021-10-28
Enregistrement modifié	2021-10-29

Date de modification :: 2024-07-17