Artificial Intelligence Data AI Problem Solving

Teaching physics to AI can enable it to make new discoveries on its own

Artificial intelligence AI problem solving

Researchers from Duke University have discovered that machine learning algorithms can gain new degrees of transparency and insight into the properties of materials after teaching them known physics.

Incorporating established physics into neural network algorithms helps them discover new insights into material properties

According to researchers at Duke UniversityIncorporating known physics into machine learning algorithms can help the enigmatic black boxes achieve new levels of transparency and insight into the properties of materials.

Researchers used a sophisticated machine learning algorithm in one of the first experiments of its kind to identify the properties of a class of engineered materials called metamaterials and to predict how they interact with electromagnetic fields.

The algorithm essentially had to show its work because it first had to take into account the known physical limitations of the metamaterial. The method not only made it possible for the algorithm to predict the properties of the metamaterial with high

How close the measured value corresponds to the correct value.

“data-gt-translate-attributes =”[{” attribute=””>accuracy, but it also did it more quickly and with additional insights than earlier approaches.

Silicon Metamaterials

Silicon metamaterials such as this, featuring rows of cylinders extending into the distance, can manipulate light depending on the features of the cylinders. Research has now shown that incorporating known physics into a machine learning algorithm can reveal new insights into how to design them. Credit: Omar Khatib

The results were published in the journal Advanced Optical Materials on May 13th, 2022.

“By incorporating known physics directly into the machine learning, the algorithm can find solutions with less training data and in less time,” said Willie Padilla, professor of electrical and computer engineering at Duke. “While this study was mainly a demonstration showing that the approach could recreate known solutions, it also revealed some insights into the inner workings of non-metallic metamaterials that nobody knew before.”

DOI: 10.1002/adom.202200097

This research was supported by the Department of Energy (DESC0014372).

#Teaching #physics #enable #discoveries

Leave a Comment

Your email address will not be published.