BETA ZEN
Mamba (deep learning architecture)
Texto da Wikipédia (en), licença CC BY-SA. O BETARUBI mostra o verbete inteiro nesta página — a leitura não continua fora do site.
Mamba is a deep learning architecture focused on sequence modeling. It was developed by two researchers Albert Gu from Carnegie Mellon University and Tri Dao from Princeton University to address some limitations of transformer models, especially in processing long sequences, and it is based on the Structured State Space sequence (S4) model.