Research team from Korea Advances Institute of Science and Technology has shared that their AI system has successfully generated new optimal nanomaterials, reads the research findings published in Science Advances on January 3.
Baekjun Kim, Sangwon Lee and Jihan Kim in their article “Inverse design of porous materials using artificial neural networks”, have shared that, in order to create a new material, they used GAN – generative adversarial network, that has a proven record of success in determining human faces.
They have trained their neural network with “a training set of 31,713 known zeolites to produce 121 crystalline porous materials”, showing the reliability in terms of designing a material, matching “user-desired” range of properties.
According to Korean scientists, these findings can potentially “accelerate materials development as it demonstrates a successful case of inverse design of porous materials”:
“Generating optimal nanomaterials using artificial neural networks can potentially lead to a notable revolution in future materials design”
As Future Time previously reported earlier, the technological advances rate of artificial intelligence technology has outpaced Moore’s Law and doubles every 3.4 months, so maybe AI could get into materials design sooner, than was earlier expected.