Recurrent Unit

Recurrent units are fundamental building blocks in recurrent neural networks (RNNs), designed to process sequential data by maintaining an internal state that evolves over time. Current research focuses on improving the efficiency and accuracy of various recurrent unit architectures, including gated recurrent units (GRUs), long short-term memory (LSTMs), and novel variations incorporating mechanisms like time delays, attention, and continuous-time formulations. These advancements are driving progress in diverse applications such as time-series forecasting, speech recognition, and video analysis, where accurately modeling temporal dependencies is crucial. The development of more efficient and robust recurrent units continues to be a significant area of research, impacting the performance of numerous machine learning models.

Papers

November 5, 2024

Pedestrian Volume Prediction Using a Diffusion Convolutional Gated Recurrent Unit Model
Yiwei Dong, Tingjin Chu, Lele Zhang, Hadi Ghaderi, Hanfang Yang
Gated Recurrent Unit Recurrent Unit Pedestrian Crossing Prediction Crowd Flow Pedestrian Prediction Model Diffusion Convolutional Recurrent Neural Network

October 7, 2024

GRU-D Characterizes Age-Specific Temporal Missingness in MIMIC-IV
Niklas Giesa, Mert Akgül, Sebastian Daniel Boie, Felix Balzer
Machine Learning Respiratory Rate Recurrent Unit Unobserved Node Different Missingness Missingness Shift

September 11, 2024

2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos
Abdarahmane Traoré, Moulay A. Akhloufi
Action Recognition Gameplay Video Gated Recurrent Unit Video Sequence Violence Detection Recurrent Unit

September 2, 2024

Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Esraa Elelimy, Adam White, Michael Bowling, Martha White
Reinforcement Learning Recurrent Neural Network Fuzzy Trace Recurrent Unit Linear Recurrent Real Time Recurrent Learning

July 19, 2024

Regression prediction algorithm for energy consumption regression in cloud computing based on horned lizard algorithm optimised convolutional neural network-bidirectional gated recurrent unit
Feiyang Li, Zinan Cao, Qixuan Yu, Xirui Tang
Cloud Computing Random Forest Model Cloud Service Recurrent Unit Regression Algorithm Energy Consumption Prediction Reptile Algorithm

January 30, 2024

Liquid Resistance Liquid Capacitance Networks
Mónika Farsang, Sophie A. Neubauer, Radu Grosu
Neural ODE Biological Neuron Recurrent Unit

June 14, 2023

Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications
David Diaz-Guerra, Archontis Politis, Antonio Miguel, Jose R. Beltran, Tuomas Virtanen
Recurrent Layer Permutation Invariant Recurrent Unit Multi Source Localization

February 16, 2023

Stabilising and accelerating light gated recurrent units for automatic speech recognition
Adel Moumen, Titouan Parcollet
Automatic Speech Recognition Gated Recurrent Unit Recurrent Unit

December 1, 2022

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
N. Benjamin Erichson, Soon Hoe Lim, Michael W. Mahoney
Discrete Time Delayed Feedback Recurrent Neural Network Architecture Recurrent Unit Gated Recurrent

November 30, 2022

Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data
Sunghyun Sim, Dohee Kim, Hyerim Bae
Recurrent Neural Network Time Series Forecasting Time Series Data Neural Network Architecture Predictive Performance Recurrent Unit Time Series Decomposition

July 1, 2022

Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml
Elham E Khoda, Dylan Rankin, Rafael Teixeira de Lima, Philip Harris, Scott Hauck, Shih-Chieh Hsu, Michael Kagan, Vladimir Loncar, Chaitanya Paikara, Richa Rao, Sioni Summers, Caterina Vernieri, Aaron Wang
Recurrent Neural Network Long Short Term Memory Field Programmable Gate Array Low Latency Neural Network Inference Recurrent Neural Network Architecture Recurrent Layer Recurrent Unit VIS4ML Research

June 28, 2022

Short-Term Plasticity Neurons Learning to Learn and Forget
Hector Garcia Rodriguez, Qinghai Guo, Timoleon Moraitis
Recurrent Unit Short Term Plasticity

May 4, 2022

GRU-TV: Time- and velocity-aware GRU for patient representation on multivariate clinical time-series data
Ningtao Liu, Ruoxi Gao, Jing Yuan, Calire Park, Shuwei Xing, Shuiping Gou
Electronic Health Record Multivariate Approach Patient Representation EHR Datasets Recurrent Unit Clinical Time Series GRU Net

March 17, 2022

Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study
Grzegorz Dudek, Slawek Smyl, Paweł Pełka
Recurrent Neural Network Comparative Study Time Series Forecasting \Sigma}{\Delta}$ Low Pas RNN RNN Architecture Recurrent Unit

February 23, 2022

Simulating Network Paths with Recurrent Buffering Units
Divyam Anshumaan, Sriram Balasubramanian, Shubham Tiwari, Nagarajan Natarajan, Sundararajan Sellamanickam, Venkata N. Padmanabhan
Network Simulation Recurrent Unit RNN Based Model

November 22, 2021

Modeling Irregular Time Series with Continuous Recurrent Units
Mona Schirmer, Mazin Eltayeb, Stefan Lessmann, Maja Rudolph
Recurrent Neural Network Irregular Time Series RNN Architecture Recurrent Unit

November 3, 2021

Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challenge
Jussi Leinonen
Solution Path Direct Convolution Neural Network Model Spatio Temporal Forecasting Shortcut Feature Convolutional Recurrent Meteorological Satellite Recurrent Unit Weather4cast Challenge

Recurrent Unit

Papers

Pedestrian Volume Prediction Using a Diffusion Convolutional Gated Recurrent Unit Model

GRU-D Characterizes Age-Specific Temporal Missingness in MIMIC-IV

2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos

Real-Time Recurrent Learning using Trace Units in Reinforcement Learning

Regression prediction algorithm for energy consumption regression in cloud computing based on horned lizard algorithm optimised convolutional neural network-bidirectional gated recurrent unit

Liquid Resistance Liquid Capacitance Networks

Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications

Stabilising and accelerating light gated recurrent units for automatic speech recognition

Gated Recurrent Neural Networks with Weighted Time-Delay Feedback

Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data

Ultra-low latency recurrent neural network inference on FPGAs for physics applications with hls4ml

Short-Term Plasticity Neurons Learning to Learn and Forget

GRU-TV: Time- and velocity-aware GRU for patient representation on multivariate clinical time-series data

Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study

Simulating Network Paths with Recurrent Buffering Units

Modeling Irregular Time Series with Continuous Recurrent Units

Spatiotemporal Weather Data Predictions with Shortcut Recurrent-Convolutional Networks: A Solution for the Weather4cast challenge