20.500.12556/DKUM-90135 Learning physical properties of liquid crystals with deep convolutional neural networks Machine learning algorithms have been available since the 1990s, but it is much more recently that they have come into use also in the physical sciences. While these algorithms have already proven to be useful in uncovering new properties of materials and in simplifying experimental protocols, their usage in liquid crystals research is still limited. This is surprising because optical imaging techniques are often applied in this line of research, and it is precisely with images that machine learning algorithms have achieved major breakthroughs in recent years. Here we use convolutional neural networks to probe several properties of liquid crystals directly from their optical images and without using manual feature engineering. By optimizing simple architectures, we fnd that convolutional neural networks can predict physical properties of liquid crystals with exceptional accuracy. We show that these deep neural networks identify liquid crystal phases and predict the order parameter of simulated nematic liquid crystals almost perfectly. We also show that convolutional neural networks identify the pitch length of simulated samples of cholesteric liquid crystals and the sample temperature of an experimental liquid crystal with very high precision. liquid crystal neural network artificial intelligence soft matter tekoči kristal nevronska mreža umetna inteligenca mehka snov true false true Nature Publishing Group Angleški jezik Slovenski jezik Znanstveno delo 2024-08-23 04:15:11 2024-11-20 14:20:42 2024-11-21 03:25:45 0000-00-00 00:00:00 2020 0 0 Str. 1-10 št. članka 7664 Letn. 10 2020 0000-00-00 Zaloznikova Objavljeno apc 2019-12-10 2020-04-03 2020-05-06 532.783:004.8 15046403 10.1038/s41598-020-63662-9 2045-2322 Sigaki-2020-Learning_physical_properties_of_li.pdf Sigaki-2020-Learning_physical_properties_of_li.pdf 1 CB9DFF107E808E66F009527732762E93 f9c0c8b08d84b9186ddf16c44d1e8efa391ec786bd199f4c3a1ec18a978b57df 1f4fb7f9-a742-11ef-a990-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=186868 https://doi.org/10.1038/s41598-020-63662-9 0 300a2c5f-a742-11ef-a990-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=186869 Fakulteta za naravoslovje in matematiko 0 0 0