What can DNNs tell us about how the brain learns? Our new results show that predictive local learning better captures changes in brain representations during statistical learning than supervised or contrastive approaches. Excellent work by @denisekittelmann.bsky.social and @gutlin.bsky.social
Predictive coding networks capture human neural representations missing in supervised DNNs
Neuroscientific learning theories propose that the brain acquires knowledge by constructing internal world models. Supervised learning, the dominant approach in deep neural networks (DNN), relies on e...
biorxiv.org
