AI models are powerful, but are they biologically plausible?

Researchers hypothesize that a powerful type of AI model known as a transformer could be implemented in the brain through networks of neuron and astrocyte cells. The work could offer insights into how the brain works and help scientists understand why transformers are so effective at machine-learning tasks.

Related Keywords

Massachusetts , United States , Konstantinos Michmizos , Kseniav Kastanenka , Dmitry Krotov , Leo Kozachkov , Research Institute , Watson Ai Lab , Proceedings Of The National Academy Sciences , Rutgers University , Department Of Brain , Harvard Medical School , Brightfocus Foundation , National Institute Of Health , Cognitive Sciences , National Academy , Massachusetts General Research , Dense Associated Memory , National Institute , Astrocytes , Transformer Model , Artificial Neural Network ,