Podcast: Could an AI Win the Nobel Prize?

Print Friendly, PDF & Email

Paul Wigley is a Postdoctoral Fellow
at the Department of Quantum Science at ANU

In this AI Podcast, Paul Wigley from the Australian National University describes how his team of scientists applied AI to an experiment to create a Bose-Einstein condensate. And in doing so they had a question: if we can use AI as a tool in this experiment, can we use AI as its own novel, scientist, to explore different parts of physics and different parts of science?

“If we were to perform a brute force search and optimize the parameters to within a 10% accuracy of the parameters maximum-minimum bounds, the number of runs required would be 1016 ,” the researchers write in the open access journal Scientific Reports.

Using the previous best online optimization algorithm, the Nelder-Mead algorithm, the Bose-Einstein condensates are able to be found much faster, in roughly 145 runs.

But with the AI program, it gets even faster: After it’s had time to learn the process, the new machine learning algorithm can find the right optimization in 10 experiments.

A simple computer program would have taken longer than the age of the universe to run through all the combinations and work this out,” Mr. Wigley said in the statement.

Download the MP3

Read the Full Story

Sign up for our insideHPC Newsletter