Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks
This work addresses efficiency improvements for recurrent neural networks, but it is incremental as it modifies existing GRU gates without introducing a new paradigm.
The paper tackled the problem of reducing computational expense in Gated Recurrent Unit (GRU) neural networks by evaluating three variants with fewer parameters in the update and reset gates, and found that these variants perform as well as the original GRU on MNIST and IMDB datasets.
The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNN) by reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while reducing the computational expense.