The brain may learn about the world the same way some computational models do

New MIT studies support the idea that the brain uses a process similar to a machine-learning approach known as “self-supervised learning.” This type of machine learning allows computational models to learn about visual scenes based solely on the similarities and differences between them, with no labels or other information.

Related Keywords

Aran Nayebi ,Rylan Schaeffer ,Ila Fiete ,Mehrdad Jazayeri ,Robert Yang ,Mikail Khona ,K Lisa Yang Icon Center ,National Institutes Of Health ,Helen Hay Whitney Foundation ,Mcgovern Institute For Brain Research ,Mcgovern Institute ,Mcknight Foundation ,Icon Center ,Simons Foundation ,Yang Integrative Computational Neuroscience ,Rishi Rajalingham ,Meta Reality Labs ,Brain Research ,Neural Information Processing Systems ,National Institutes ,Helen Hay Whitney ,Self Supervised Learning ,Grid Cells ,Computational Models ,