AI can tell where a mouse is by reading its brain activity

Analyzing a mouse’s brain activity tells scientists where the animal is located and in which direction it is looking. With further research, the findings could one day help robots navigate autonomously.

Mammals the brain Use two main types of neurons for navigation: “head direction cells” that show where the animal is facing and “grid cells” that help provide a two-dimensional brain map of where they are. located in.

To learn more about the firing of these neurons, Vasilios Marulus at the University of Tennessee, Knoxville, and his colleagues — in conjunction with the U.S. Army Research Laboratory — analyzed data from a previous study.

In this experiment, probes were inserted into the brains of several mice. Data from their neural firing patterns was then combined with video footage showing their locations and head positions as they moved around in an open environment.

From this, Maroulas and his colleagues developed a Artificial intelligence Algorithms that can work out where the mouse is looking and where it is located.

In effect, it’s similar to droppins and directional arrows on a smartphone’s map app, except linked to a GPS satellite, scientists analyze a subject’s brain activity.

“This method allows us to rely on a pre-loaded map or update GPS coordinates based on satellite data,” says Marouls. “In a sense, the algorithm ‘thinks’ and perceives space like a mammalian brain.”

AI could eventually enable intelligent systems to navigate autonomously, he says. “In other words, we take advantage of how the mammalian brain processes data and incorporate it into the architecture of the algorithm.”

Adam Hines Australia’s Queensland University of Technology says the analogy of a smartphone app is helpful. “You have positional information (droppins) associated with directions (blue arrows) and during navigation, both are constantly updated as you move. Grid cells are like GPS and heading cells are like compasses. .