Concept
GRU
A GRU (Gated Recurrent Unit) is a type of recurrent neural network layer that processes a sequence one step at a time, carrying a hidden state vector that summarizes everything seen so far. Think of it like an LSTM, except with fewer moving parts: it drops the separate cell…
The rest of “GRU” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→