“Hearst and Yahoo magazines can earn a commission or revenue from some items through these links.”
Here’s what you will learn when you read this story:
-
For all the problems that the AI causes society, one of its biggest benefits lies in the world of science.
-
A new study focused on the chaotic dynamics of dusty plasma has found that when it is trained properly, AI can actually find new physics in itself.
-
By providing the most detailed description of this type of matter, AI corrects long-standing theoretical beliefs about how particles behave in dusty plasma.
In more than one way, artificial intelligence worsens the world. Now the generative AI issues countless amounts of “AI Slopp”, and in classrooms AI is slowly eroding the critical thinking skills that are … you know … criticallyS This is not even mentioned the unfortunate role of AI as an environmental decimer and destroyer of work.
Fortunately, some models of artificial intelligence and machine learning (ml) have more ambitions than detachment Beloved animators and mass production of eighth -grade reading levels. Take, for example, a new ML model developed by a team of scientists at Emory University. Usually, machine learning algorithms are used as a tool to help scientists sift huge amounts of data or optimize experiments, but this particular ML model actually discovers new physics on its own because it is related to the dusty plasma.
You are probably familiar with the plasma – this fourth state of matter that actually presents 99.9% of all ordinary materials in the universeS The muzzle plasma is just the same mixture of ionized gas, but with charged particulate matter. This type of plasma can be found both in space and in the earth’s environment. Wild fires, for example, generate dusty plasma when they loaded soot particles mixed with smoke. In this new study – published in the magazine Works of the National Academy of Sciences (PNAS)-A researchers’ decree describes how their trained ML model has successfully provided the most detailed description of dusty plasma physics so far, creating accurate forecasts for non-reciprocal forces.
“Our AI method is not a black box: we understand how and why it works,” says Justin Burton, co -author of Emori study, in a press statement. “The frame it provides is also universal. It can potentially apply to other many body systems to open new routes to detect.”
To put it simply, non-reciprocal forces (as their name implies) when the forces exercised between two particles in plasma are not the same. The authors describe the phenomenon as two boats affected by the following – the relative situation can affect the attractive or repulsive particles.
“In dusty plasma, we have described how a leading particle attracts the delayed particle, but the back particle always repels the leader,” says Elijah Nemenman, another co -author of Emori’s study. “This phenomenon was expected by some, but now we have the exact approximation of it that did not exist before.”
The ML algorithm has also been able to correct some theoretical misconceptions about dusty plasma. For example, scientists believe that the charge of the particle is proportional to its size, but the model confirms that although the greater particle contains a larger charge, it is not proportional as it can be influenced by density and temperature. They also found that the charge between the particles was not only affected by the distance between two particles, but also by the dimensions of the particles.
One of the most difficult parts of this project, according to the authors, was the first to design the ML algorithm. Overall, AI acquires its abilities by eating (or trains data sets) -give AI a million monkey photos and will be better better when identifying a monkey when he sees it. However, when it comes to discovering New Physics, there is not much training data. So the team had to create a structure to allow it to work with the data do Have you to give him a latitude to examine unknown physics.
“I think about it like the Star Trek motto to go boldly where no one has before,” Burton said. “Used correctly, AI can open doors for all new spheres to explore.”
You may like and