The first simulation of the Universe based on AI has been developed. The neural network performs its work so well that it is even strange

Three-dimensional model of the universe, which was able to build with the help of a new algorithm

A few days ago, the first emulator of the universe based on artificial intelligence was introduced. The developers claim that the emulator is fast and accurate enough, the creators of the project are even surprised that the AI ​​“understands” some factors that he shouldn’t know about.

In general, the idea of ​​modeling the universe is not new: scientists have used computer simulations to evaluate the evolutionary processes taking place in the universe for many decades. Previously, projects based on traditional methods that demonstrate acceptable results have already been demonstrated. But now something new has appeared - an emulator of the Universe based on machine learning. This system allows you to get the desired results in milliseconds.

This is what the developers say about their project: “We built a neural network based on deep machine learning to evaluate the structure of the Universe. The project shows better results than standard systems, extrapolating the data obtained beyond the limits of the presented AI model. ”
')
So, if the AI ​​provides gravity data, it will quickly calculate other variables and data that were not provided to the system. An example is the case with the calculation of the amount of dark matter.

So, the team did not train its system, which was called the Deep Density Displacement Model (D3M), on the data, where dark matter would be taken into account. Neural network simply did not have corresponding data. Nevertheless, she was able to independently calculate all the parameters, having managed with the data that she had.

“This situation can be compared to the neural network that was taught to recognize cats and dogs, but she learned to identify elephants herself. No one knows how this happened, this riddle has yet to be solved, ”the project leader said.

The simulator itself was designed to help astrophysicists and other scientists who explore space, fill in the gaps in the history of our Universe.

The fact is that in fact it is a very strange and mysterious place. Mankind is only beginning to gradually understand the laws that made it possible to form the modern world in the form in which we know it. Artificial intelligence can help us to understand exactly how the development of the Universe took place and in which direction evolution will move on.

The AI ​​was developed by a team of scientists from the Center for Computational Astrophysics at the Flatiron Institute in New York. Computer simulation has allowed to give into the hands of astrophysicists an effective tool to understand how space will evolve under different scenarios. Modeling requires many thousands of operations, but the system handles everything just fine.

It is worth noting that researchers provide their system only data on gravity, considering that it allows you to determine most of the processes that occur at the level of planets and stars.

At the very beginning, experts trained their neural network based on more than 8,000 different simulations of the Universe , created earlier with the help of other programs. As a result, when the new algorithm was launched, it gave the opportunity to recreate the model of the Universe with a diameter of 600 million light years in just 30 ms. The error compared with other programs was no more than 3%, despite the fact that traditional systems spent more than 300 hours on a similar task.