This AI Paper Introduces POYO-1: An Artificial Intelligence Framework Deciphering Neural Activity across Large-Scale Recordings with Deep Learning

Researchers from Georgia Tech, Mila, Université de Montréal, and McGill University introduce a training framework and architecture for modeling neural population dynamics across diverse, large-scale neural recordings. It tokenizes individual spikes to capture fine temporal neural activity and employs cross-attention and a PerceiverIO backbone. A large-scale multi-session model is constructed from data from seven nonhuman […]

The post This AI Paper Introduces POYO-1: An Artificial Intelligence Framework Deciphering Neural Activity across Large-Scale Recordings with Deep Learning appeared first on MarkTechPost …

ai paper ai shorts applications architecture artificial artificial intelligence attention deep learning diverse dynamics editors pick framework georgia georgia tech intelligence machine learning mcgill university modeling paper population researchers scale staff tech tech news technology temporal training university