Artificial intelligence or AI algorithms trained on real astronomical observations will accelerate the rate of discovery. However, astronomers at the University of California, Berkeley, have discovered that AI can reveal unsuspected connections hidden in complex mathematics arising from general relativity – especially how That idea is applied to the discovery of new planets around other stars. An AI algorithm was built to locate alien planets faster when such planetary systems pass in front of a background star and temporarily brighten it – known as gravitational microlensing – revealed that the theories used to explain these findings were incomplete.
Albert Einstein How was it proven in 1936? Gravitation of a foreground star can bend light from a distant star, not only illuminating it when seen from The earth but also split it into points of light or bend it into a ring, now known as an Einstein ring.
Brightening over time is more complicated when the foreground subject is a star with planet. Furthermore, there are many planetary orbits that can also explain a certain light curve, known as degeneracy. Humans have simplified the math and missed the bigger picture as a result.
The WHO On the other hand, the algorithm shows a mathematical way to unify the two main types of degeneracy in explaining what the telescope detects during microlensing. According to the researchers, it proves that the two theories are actually special cases of a broader, yet incomplete theory. They have Be recorded Their findings are published in a paper in the journal Nature Astronomy.
Joshua Bloom, UC Berkeley professor of astronomy and chair of the department, has written in a blog post a few months ago that they had discovered something new and essential about the equations governing the generality relativistic effect of light bent by two weights, thanks to a machine learning deductive approach they had developed earlier.
Bloom linked UC Berkeley graduate student Keming Zhang’s discovery to the connections established by GoogleDeepMind’s AI team, between two fields of math. These examples demonstrate that AI systems can uncover fundamental relationships that humans miss.
Bloom says that in his opinion, they are among the first instances of AI being used to directly provide new theoretical knowledge in mathematics and astronomy. They were looking for an AI framework to act as an intellectual rocket ship for scientists, like Steve Jobs Bloom said computers can be mental bicycles.
Co-author Scott Gaudi, a professor of astronomy at Ohio State University, says that this is a major milestone in AI and machine learning. Experts in the field who have worked with data for decades ignored this degeneration until Keming’s machine learning method identified it.
