GRU
or: Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
This paper introduces the “Hidden Unit that Adaptively Remembers and Forgets”, later known as the Gated Recurrent Unit, or GRU.
from a laptop in Sunnyvale
or: Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
This paper introduces the “Hidden Unit that Adaptively Remembers and Forgets”, later known as the Gated Recurrent Unit, or GRU.