Going Beyond Linear Transformers with Recurrent Fast Weight Programmers.

Kazuki Irie Imanol Schlag Róbert Csordás Jürgen Schmidhuber

Published in: CoRR (2021)

Keyphrases

feed forward
multiscale
software engineering
software development
recurrent neural networks
database
data sets
social networks
case study
database systems
object oriented
general purpose
sufficient conditions
linear systems
weight vector