Poster
On Multiplicative Integration with Recurrent Neural Networks
Yuhuai Wu · Saizheng Zhang · Ying Zhang · Yoshua Bengio · Russ Salakhutdinov

Tue Dec 6th 06:00 -- 09:30 PM @ Area 5+6+7+8 #96 #None

We introduce a general simple structural design called “Multiplicative Integration” (MI) to improve recurrent neural networks (RNNs). MI changes the way of how the information flow gets integrated in the computational building block of an RNN, while introducing almost no extra parameters. The new structure can be easily embedded into many popular RNN models, including LSTMs and GRUs. We empirically analyze its learning behaviour and conduct evaluations on several tasks using different RNN models. Our experimental results demonstrate that Multiplicative Integration can provide a substantial performance boost over many of the existing RNN models.

Author Information

Yuhuai Wu (University of Toronto)
Saizheng Zhang (University of Montreal)
Ying Zhang (University of Montreal)
Yoshua Bengio (U. Montreal)
Russ Salakhutdinov (University of Toronto)

More from the Same Authors