Title: Target-learning the Latent Space of a Variational Autoencoder model for the Inverse Design of Stable Perovskites.
Accepted for publication at the 36th Canadian Conference on Artificial Intelligence (Montreal, June-2023). https://www.doi.org/10.21428/594757db.07402193
Ericsson Tetteh Chenebuah [1,2,*], Michel Nganbe [1] and Alain Beaudelaire Tchagang [2]
[1] Department of Mechanical Engineering, University of Ottawa, 161 Louis-Pasteur, Ottawa, ON, K1N 6N5 Canada.
[2] Digital Technologies Research Centre, National Research Council of Canada, 1200 Montréal Road, Ottawa, ON, K1A 0R6 Canada.
*Corresponding author: echen013@uottawa.ca
The study develops an inverse design machine learning pipeline by combining a generative Variational AutoEncoder (VAE) model with Target-Learning (TL) feed-forward neural networks to form the TL-VAE perovskite generator. The results report the discovery of promising new perovskite candidates of the ABX3 generic, which are unique and polymorphic material variants.
This research was supported by the National Research Council of Canada (NRC) through its Artificial Intelligence for Design Program led by the Digital Technologies Research Centre.
[1] J. Noh et al., Matter, 1(5), (2019), 1370-1384. https://doi.org/10.1016/j.matt.2019.08.017
[2] Z. Ren et al., Matter, 5(1), (2022), 314-335. https://doi.org/10.1016/j.matt.2021.11.032
[3] E.T. Chenebuah et al., Mater. Res. Express., (2023). https://doi.org/10.1088/2053-1591/acb683
If you are using this resource please cite as:
@article{Chenebuah2023Target,
author = {Chenebuah, Ericsson and Nganbe, Michel and Tchagang, Alain},
journal = {Proceedings of the Canadian Conference on Artificial Intelligence},
year = {2023},
month = {jun 5},
note = {https://caiac.pubpub.org/pub/z0v0g7l7},
publisher = {Canadian Artificial Intelligence Association (CAIAC)},
title = {Target-learning the {Latent} {Space} of a {Variational} {Autoencoder} model for the {Inverse} {Design} of {Stable} {Perovskites}},
}