A neural network discovered Copernicus’ heliocentricity on its own

Can neural networks help scientists discover laws about more complex phenomena, like quantum mechanics?

A neural network discovered Copernicus’ heliocentricity on its own
  • Scientists trained a neural network to predict the movements of Mars and the Sun.
  • In the process, the network generated formulae that place the Sun at the center of our solar system.
  • The case suggests that machine-learning techniques could help reveal new laws of physics.


A neural network was able to rediscover one of the most important paradigm shifts in scientific history: Earth and other planets revolve around the Sun. The accomplishment suggests machine-learning techniques could someday help to reveal new laws of physics, maybe even within the complex realm of quantum mechanics.

The results are set to appear in the journal Physical Review Letters, according to Nature.

The neural network — a machine-learning algorithm called SciNetwas shown measurements of how the Sun and Mars appear from Earth against the fixed-star background of the night sky. SciNet's task, assigned by a team of scientists at the Swiss Federal Institute of Technology, was to predict where the Sun and Mars would be at future points in time.

Copernicus-style formulae

In the process, SciNet generated formulas that place the Sun at the center of our solar system. Remarkably, SciNet accomplished this in a way similar to how astronomer Nicolaus Copernicus discovered heliocentricity.

"In the 16th century, Copernicus measured the angles between a distant fixed star and several planets and celestial bodies and hypothesized that the Sun, and not the Earth, is in the centre of our solar system and that the planets move around the Sun on simple orbits," the team wrote in a paper published on the preprint repository arXiv. "This explains the complicated orbits as seen from Earth."

The team "encouraged" SciNet to come up with ways to predict the movements of the Sun and Mars in the simplest way possible. To do that, SciNet passes information back and forth between two sub-networks. One network "learns" from data, and the other uses that knowledge to make predictions and test their accuracy. These networks are connected to each other by only a few links, so when they communicate, information is compressed, resulting in "simpler" representations.

Renner et al.

SciNet decided that the simplest way to predict the movements of celestial bodies was through a model that places the Sun at the center of our solar system. So, the neural network didn't necessarily "discover" heliocentricity, but rather described it through mathematics that humans can interpret.

Building humanlike AI

In 2017, data scientist Brenden Lake and his colleagues wrote a paper describing what it will take to build machines that learn and think like people. One benchmark for doing so would be artificial intelligence that can describe the physical world. At the time, they said it "remains to be seen" whether "deep networks trained on physics-related data" could discover laws of physics on their own. In a narrow sense, SciNet passes this test.

"To summarize, the main aim of this work is to show that neural networks can be used to discover physical concepts without any prior knowledge," the SciNet team wrote. "To achieve this goal, we introduced a neural network architecture that models the physical reasoning process. The examples illustrate that this architecture allows us to extract physically relevant data from experiments, without imposing further knowledge about physics or mathematics."

No, the Yellowstone supervolcano is not ‘overdue’

Why mega-eruptions like the ones that covered North America in ash are the least of your worries.

Ash deposits of some of North America's largest volcanic eruptions.

Image: USGS - public domain
Strange Maps
  • The supervolcano under Yellowstone produced three massive eruptions over the past few million years.
  • Each eruption covered much of what is now the western United States in an ash layer several feet deep.
  • The last eruption was 640,000 years ago, but that doesn't mean the next eruption is overdue.
Keep reading Show less

Do you worry too much? Stoicism can help

How imagining the worst case scenario can help calm anxiety.

Stoicism can help overcome anxiety

Credit: OLIVIER DOULIERY via Getty Images
Personal Growth
  • Stoicism is the philosophy that nothing about the world is good or bad in itself, and that we have control over both our judgments and our reactions to things.
  • It is hardest to control our reactions to the things that come unexpectedly.
  • By meditating every day on the "worst case scenario," we can take the sting out of the worst that life can throw our way.
Keep reading Show less

Study: People will donate more to charity if they think something’s in it for them

A study on charity finds that reminding people how nice it feels to give yields better results than appealing to altruism.

How to get people to want to give you money, literal balls of cash not gaurenteed.

Photo by Pixabay from Pexels
Personal Growth
  • A study finds asking for donations by appealing to the donor's self-interest may result in more money than appealing to their better nature.
  • Those who received an appeal to self-interest were both more likely to give and gave more than those in the control group.
  • The effect was most pronounced for those who hadn't given before.
Keep reading Show less
Surprising Science

160-million-year-old ‘Monkeydactyl’ was the first animal to develop opposable thumbs

The 'Monkeydactyl' was a flying reptile that evolved highly specialized adaptations in the Mesozoic Era.

Quantcast