Sign In

Communications of the ACM

ACM TechNews

Decoding Canine Cognition

The results of the research suggest that dogs are more attuned to actions in their environment, rather than to who or what is doing the action.

Credit: Getty Images

Emory University researchers have decoded visual images from a dog's brain.

The researchers captured functional magnetic resonance imaging (fMRI) neural data of two dogs as they viewed videos for 90 minutes in total, then analyzed their brain-data patterns using a machine learning algorithm.

They time-stamped the video data into classifiers, including object-based classifiers and action-based classifiers; the time stamps mapped the brain data onto the classifiers.

The Ivis algorithm decoded the action classifiers, but not the object classifiers, with 75% to 88% accuracy.

"We showed that we can monitor the activity in a dog's brain while it is watching a video and, to at least a limited degree, reconstruct what it is looking at," explained Emory's Gregory Berns.

From Emory University
View Full Article


Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


No entries found