Sign In

Communications of the ACM

ACM TechNews

Studying the Big Bang with AI

View as: Print Mobile App Share:
A quark gluon plasma after the collision of two heavy nuclei.

The new type of neural network provides a promising tool for describing physical phenomena that other computational methods are not sufficiently powerful to handle.

Credit: Andreas Ipp et al

Researchers at Austria's TU Wien have demonstrated that neural networks can be used to simulate "quark-gluon plasma" to study the Big Bang.

The researchers developed a neural network that automatically takes into account gauge symmetries, so different representations of the same physical state produces the same signals in the neural network.

Said TU Wien's Andreas Ipp, "With such neural networks, it becomes possible to make predictions about the system—for example, to estimate what the quark-gluon plasma will look like at a later point in time without really having to calculate every single intermediate step in time in detail. And at the same time, it is ensured that the system only produces results that do not contradict gauge symmetry—in other words, results which make sense at least in principle."

The researchers found that fully simulating atomic core collisions using these methods will take time.

From TU Wein (Austria)
View Full Article


Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account