Gated recurrent unit
Appearance
This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages)
|
Gated recurrent units are a gating mechanism in recurrent neural networks, introduced in 2014. Their performance on polyphonic music modeling and speech signal modeling was found to be similar to that of long short-term memory.[1] They have fewer parameters than LSTM, as they lack an output gate.[2]
Architecture
. denotes the Hadamard product.
Variables
- : input vector
- : output vector
- : update gate vector
- : reset gate vector
- , and : parameter matrices and vector
- : The original is a sigmoid function.
- : The original is a hyperbolic tangent.
References
- ^ Chung, Junyoung; Gulcehre, Caglar; Cho, KyungHyun; Bengio, Yoshua (2014). "Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling". arXiv:1412.3555 [cs.NE].
- ^ "Recurrent Neural Network Tutorial, Part 4 – Implementing a GRU/LSTM RNN with Python and Theano – WildML". Wildml.com. Retrieved May 18, 2016.