No account yet ?

Gated recurrent units are a gating mechanism in recurrent neural networks

Closed recurrent unit (GRU) is like a long short term memory with a forgetting gate with less parameters than LSTM which has no exit gate.

The performance of the closed recurrent unit (GRU) on certain polyphonic music modeling, speech signal modeling and natural language processing tasks was found to be similar to that of LSTM.

Closed Recurrent Units (GRUs) have been shown to perform better on some smaller and less frequent datasets.