Some computational neuroscientists say self-supervised AI learning models have shown a closer correspondence to brain function than supervised-learning models (Anil Ananthaswamy/Quanta Magazine)

Anil Ananthaswamy / Quanta Magazine:
Some computational neuroscientists say self-supervised AI learning models have shown a closer correspondence to brain function than supervised-learning models  —  Self-supervised learning allows a neural network to figure out for itself what matters.  The process might be what makes our own brains so successful.