"When the researchers tested the model on around 1,500 brain scans, it could almost always tell if the scan came from a woman or a man."
It's pretty cool to see blackbox models derive reliable signals from basically raw data. However, the results don't really imply sex differences are biological in nature if I'm reading correctly. Being raised male/female probably has some profound impacts on the brain (these were adult brains). I bet a similar methodology would be able to tell who played American football growing up...
"When the researchers tested the model on around 1,500 brain scans, it could almost always tell if the scan came from a woman or a man."
It's pretty cool to see blackbox models derive reliable signals from basically raw data. However, the results don't really imply sex differences are biological in nature if I'm reading correctly. Being raised male/female probably has some profound impacts on the brain (these were adult brains). I bet a similar methodology would be able to tell who played American football growing up...