Gated Recurrent Unit

Also known as GRU

Follow this topic Ask about this topic

Latest papers

18 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Gate Initialisation versus Recurrent Dropout and Zoneout in Learning Long Dependencies: A Controlled Study of LSTM and GRU Networks on Synthetic Tasks
Oct 21, 2026Oleksandr Kholodniak, Oleksandr ProkhorovRecurrent Neural Networks Long Short-Term Memory Networks
National Aerospace University “Kharkiv Aviation Institute”, Kharkiv, Ukraine
The RNN Homunculus: Learning to Gate Long-Term Memory
Oct 9, 2026Zeyu Fan, Alexandru-Dragos Manolache, Jan van GemertLong-Range Dependency Modeling Recurrent Neural Networks
Delft University of Technology, Mekelweg 5, 2628 CD Delft, The Netherlands
Bounded Channel-Adaptive Spectral Learning for Forward-Consistent Inverse Flapping-Wing Aerodynamics
Sep 30, 2026Haichuan LiGated Recurrent Unit Recurrent Neural Networks
University of Turku
BreathGRU: A Novel Semi-Supervised Bidirectional Gated Recurrent Unit Framework for Speech and Breath Segmentation for Respiratory Audio
Sep 25, 2026Sania Fatima Sayed, John W. Holloway, Reyer Zwiggelaar +1Gated Recurrent Unit Speech Processing
Department of Computer Science, Aberystwyth University, Aberystwyth, United Kingdom, UK SY23 3DB · Human Development and Health, Faculty of Medicine, University of Southampton, United Kingdom, SO16 6YD
Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modelling
Sep 3, 2026Alessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami +2Gated Recurrent Unit Recurrent Neural Networks
SISTEMA GmbH, Vienna, Austria · Beyond EO, Paris, France
DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model
Aug 19, 2026Kyung Min Han, Eunsom Kim, Young J. KimGated Recurrent Unit Robot Navigation
A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX30
Jul 15, 2026Muhammed Walid, Ahmed El-Naeimy, Hosam Moubarak +1Gated Recurrent Unit Long-Term Time Series Forecasting
Cyber Physical Lab, Department of Computer Science & Engineering · Egypt-Japan University Of Science and Technology, Alexandria, Egypt · Accounting Department +1
Dzongkha Next Word Prediction System
Jul 13, 2026Prerna Chhetri, Tenzin Yoezer, Phuntsho Wangmo +1Gated Recurrent Unit Next-Token Prediction
Information Technology Department, College of Science and Technology, Royal University of Bhutan
Towards Explainable Adjudicative Variance: Quantifying Judicial Discretion via Gated Multi-Task Learning
Jun 25, 2026Stanisław Sójka, Felix Steffek, Matthias GrabmairGated Recurrent Unit Legal NLP
School of Computation, Information, and Technology, Technical University of Munich, Germany · Faculty of Law, University of Cambridge
LK Jam: System Architecture and Implementation of a Real-Time Human-AI Interactive Music Generation System using Role-Aware GRU
Jun 19, 2026Yakun Liu, Zhiyu Jin, Dong Liu +1Gated Recurrent Unit Music Generation
Yakun Liu, Dong Liu, and Hai Luan are with the Shenyang Conservatory of Music. · Z. Jin is an independent collaborator.
From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers
Jun 15, 2026Emre Can KizilatesGated Recurrent Unit Efficient Neural Network Inference
Independent Researcher, Izmir, Turkey
A Random-Matrix Criterion for Initializing Gated Recurrent Neural Networks
May 11, 2026Tommaso Fioratti, Riccardo Marcaccioli, Francesco CasolaGated Recurrent Unit Neural Network Initialization
Capital Fund Management, 75007 Paris, France · Institute of Mathematics, EPFL, 1015 Lausanne, Switzerland
C2L-Net: A Data-Driven Model for State-of-Charge Estimation of Lithium-Ion Batteries During Discharge
May 9, 2026Khoa Tran, T. Nguyen-Thoi, Vin Nguyen-Thai +3Gated Recurrent Unit Causal Attention
Data Science Laboratory, Faculty of Information Technology, Ton Duc Thang University, Ho Chi Minh City, Vietnam. · Laboratory for Applied and Industrial Mathematics, Institute for Computational Science and Artificial Intelligence, Van Lang University, Ho Chi Minh City, 70000, Viet Nam. · Faculty of Mechanical, Electrical, and Computer Engineering, Van Lang School of Technology, Van Lang University, Ho Chi Minh City, 70000, Viet Nam. +6
Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM
May 3, 2026Luo Ji, Qi Qin, Ningyuan Xi +3Gated Recurrent Unit Meta-Learning
Geely AI Lab, Geely Auto Group, Zhejiang, China · Peking University, Beijing, China
Learning-Based Dynamics Modeling and Robust Control for Tendon-Driven Continuum Robots
Apr 28, 2026Ziqing Zou, Ke Qiu, Fei Wang +3Gated Recurrent Unit Robot Trajectory Tracking
Department of Control Science and Engineering, Zhejiang University, Hangzhou, China
Real-Time Thermal-Inertial Odometry on Embedded Hardware for High-Speed GPS-Denied Flight
Mar 2, 2026Austin Stone, Mark Petersen, Cammy PetersonGated Recurrent Unit Inertial Odometry
Brigham Young University, Provo, UT 84602 USA.
DReX: An Explainable Deep Learning-based Multimodal Recommendation Framework
Feb 23, 2026Adamya Shyam, Venkateswara Rao Kagita, Bharti Rana +1Gated Recurrent Unit Multimodal Recommendation
University of Delhi, Delhi, India · National Institute of Technology, Warangal, India
Learnability Window in Gated Recurrent Neural Networks
Dec 5, 2025Lorenzo LiviGated Recurrent Unit Recurrent Neural Networks
OPIT – Open Institute of Technology

Oct 21, 2026J/K move · Enter open · S save

Gate Initialisation versus Recurrent Dropout and Zoneout in Learning Long Dependencies: A Controlled Study of LSTM and GRU Networks on Synthetic Tasks

Oleksandr Kholodniak, Oleksandr Prokhorov

National Aerospace University “Kharkiv Aviation Institute”, Kharkiv, Ukraine

Recurrent Neural Networks Long Short-Term Memory Networks Long-Range Dependency Modeling Gated Recurrent Unit Neural Network Initialization

Open paper AskPDF arXiv

Dropout and zoneout are routinely added to long short-term memory (LSTM) and gated recurrent unit (GRU) networks, but, to our knowledge, their placements have not been crossed with gate initialisation in a factorial design, and it is not known whether early gradient propagation tells which runs will learn long dependencies. We trained one-layer LSTMs and GRUs on the adding problem and on delayed recall in a factorial grid of 720 runs, crossing conventional and chrono gate initialisation with up to six recurrent regulariser placements at one rate each, with pre-specified follow-ups, and recorded how sensitive the final hidden state was to the input at every lag. Because both tasks supply fresh or exhaustive training data, the study measures the regularisers' effects on optimisation and does not assess generalisation from a finite training set. At lengths chosen to make conventional initialisation difficult, all 360 chrono-initialised runs reached the validation criterion within 5000 updates, as did 119 of 120 unregularised runs with a horizon about four times too short or too long, whereas conventionally initialised networks learned slowly or did not reach the criterion within the budget at the longer lengths. Under conventional initialisation, dropout generally delayed learning and zoneout helped only in some conditions. The early input sensitivity added little to predicting which conditions learn once the early validation loss was modelled per task, architecture and initialisation. Within conditions, a flatter early decay went with the seeds that learned, but in a pre-specified test the association was modest (concordance 0.61), condition-dependent and not robust to resampling seeds. The results support chrono initialisation, even with a rough horizon, on such tasks.