Timezone: »

Complex Gated Recurrent Neural Networks
Moritz Wolter · Angela Yao

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 210 #93

Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures. RNNs, widely used to process time series and sequence information, could greatly benefit from complex representations. We present a novel complex gated recurrent cell, which is a hybrid cell combining complex-valued and norm-preserving state transitions with a gating mechanism. The resulting RNN exhibits excellent stability and convergence properties and performs competitively on the synthetic memory and adding task, as well as on the real-world tasks of human motion prediction.

Author Information

Moritz Wolter (University of Bonn)
Angela Yao (National University of Singapore)

More from the Same Authors