Complex Gated Recurrent Neural Networks

2018/06/21 by Moritz Wolter, Wolter, Moritz, Angela Yao +1 · 5 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Human Motion and Animation #Human Pose and Action Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Video Analysis and Summarization

paper · pdf · doi:10.48550/arxiv.1806.08267

openalex publication_date 2018/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• On the difficulty of training Recurrent Neural Networks
• Long Short-Term Memory
• The Complex Gradient Operator and the CR-Calculus
• ImageNet classification with deep convolutional neural networks
• Associative Long Short-Term Memory
• On Complex Valued Convolutional Neural Networks
• Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Cited by

• BeatFormer: Efficient motion-robust remote heart rate estimation through unsupervised spectral zoomed attention filters
• Revisiting Bi-Linear State Transitions in Recurrent Neural Networks
• A Survey of Deep Learning for Complex Speech Spectrograms
• Analysis of Deep Complex-Valued Convolutional Neural Networks for MRI\n Reconstruction
• Complex Unitary Recurrent Neural Networks using Scaled Cayley Transform

Related

• Complex Recurrent Spectral Network
• Sequence Modeling using Gated Recurrent Neural Networks
• Gated Feedback Recurrent Neural Networks
• Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
• Gates Are Not What You Need in RNNs