1 code implementation • ACL 2022 • Pedro Henrique Martins, Zita Marinho, Andre Martins
Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length.
no code implementations • NeurIPS 2014 • Renato Negrinho, Andre Martins
We propose a general framework for regularization based on group majorization.