The AI uses data from 199 earthquakes and the more than 130,000 aftershocks. Manual predictions are possible but they consume time and have proven to be less accurate than those of the AI.

Many believe aftershocks occur within a short timeframe of an earthquake. The AI, however, can predict aftershocks up to a year after the initial event.

No seismologists took part in the research, though two of its lead researchers – Phoebe DeVries of the Department of Earth and Planetary Sciences at Harvard, and Google AI recruiting lead Brendan Meade – consider themselves to be computational earth scientists.

Two other machine learning researchers from Google were involved with the project; Martin Wattenberg, and Fernanda Viégas.

The results of the project were published in the science journal ‘Nature’ today.

Nature came under fire earlier this year for a decision to lock its upcoming machine learning section behind a paywall.

Thousands of researchers are boycotting the journal as a result of their belief in open AI research. The researchers believe in sharing findings to both advance developments and promote ethical standards.

As of writing, the petition against the move features 3352 signatories.

What are your thoughts on the use of AI to predict natural disasters?

The post Harvard and Google partner on earthquake aftershock-predicting AI appeared first on AI News.

Fully understanding the ‘internal GPS’ used by humans and other mammals to navigate from point A to B has eluded neuroscientists for decades. By analysing a new AI, which developed ‘grid cells’ similar to our brains, researchers believe we could be closer than ever.

The new AI was designed by a team from Google DeepMind and University College London to navigate a virtual environment from one point to another in the most efficient way possible.

In findings posted to science journal Nature, the AI developed grid cells similar to mammals. Grid cells were first discovered in 2005 by Norwegian neuroscientists May-Britt and Edvard Moser, earning them a share of the 2014 medicine Nobel Prize.

The neuroscientists made their discovery after observing rats navigating and finding grid cells in their brains firing at points which formed a hexagonal pattern.

Animation provided by DeepMind

Grid cells work in combination with other brain cells. This includes ‘place cells’ which activate when a mammal is in a specific location, and ‘head direction cells’ which fire when the head is pointed in a specific direction.

How all of these cells work together is less well known, but the researchers are hoping to find some answers by observing the AI. They expect this will be just the start in using AI to gain a greater understanding of biology.

You can find the formatted Nature paper here, but note that it’s behind a controversial paywall. Alternatively, the unformatted full paper is available free here (PDF).

What are your thoughts on the use of AI to gain a deeper understanding of biology?

The post Virtually Brainy: AI wires itself to navigate like mammals appeared first on AI News.