mlsanityData to 14 Oct 2026

Minimal Gated Unit for Recurrent Neural Networks

arXiv 1603.09420 ↗First posted 31 Mar 2016cs.NE cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden units (such as LSTM and GRU). We propose a gated unit for RNN, named as Minimal Gated Unit (MGU), since it only contains one gate, which is a minimal design among all gated hidden units. The design of MGU benefits from evaluation results on LSTM and GRU in the literature. Experiments on various sequence data show that MGU has comparable accuracy with GRU, but has a simpler structure, fewer parameters, and faster training. Hence, MGU is suitable in RNN's applications. Its simple architecture also means that it is easier to evaluate and tune, and in principle it is easier to study MGU's properties theoretically and empirically.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 7; 2023: 8; 2024: 4; 2025: 10; 2026: 5.

40 papers.

Sort:

By area:

  1. 2024Gated Slot Attention for Efficient Linear-Time Sequence Modelingcited by 76
  2. 2024A Survey of Deep Learning and Foundation Models for Time Series Forecastingcited by 33
  3. 2022Rapid training of quantum recurrent neural networkscited by 13
  4. 2022Recurrent networks, hidden states and beliefs in partially observable environmentscited by 12
  5. 2025Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modelingcited by 10
  6. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  7. 2024Recurrent neural network wave functions for Rydberg atom arrays on kagome latticecited by 8
  8. 2025Self-Supervised Sparse Sensor Fusion for Long Range Perceptioncited by 8
  9. 2022Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillationcited by 7
  10. 2022Supplementing Recurrent Neural Network Wave Functions with Symmetry and Annealing to Improve Accuracycited by 6
  11. 2023Investigating Topological Order using Recurrent Neural Networkscited by 6
  12. 2023PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensorscited by 6
28 more
  1. 2021Topos and Stacks of Deep Neural Networkscited by 5
  2. 2022What is the best RNN-cell structure to forecast each time series behavior?cited by 5
  3. 2022ICE-NODE: Integration of Clinical Embeddings with Neural Ordinary Differential Equationscited by 5
  4. 2023Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environmentscited by 5
  5. 2023Learning with Chemical versus Electrical Synapses -- Does it Make a Difference?cited by 5
  6. 2021Warming up recurrent neural networks to maximise reachable multistability greatly improves learningcited by 3
  7. 2022ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecastingcited by 3
  8. 2025Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detectioncited by 3
  9. 2021Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directionscited by 2
  10. 2023Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecastingcited by 2
  11. 2021Gates Are Not What You Need in RNNscited by 1
  12. 2021ARISE: ApeRIodic SEmi-parametric Process for Efficient Markets without Periodogram and Gaussianity Assumptionscited by 1
  13. 2023Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applicationscited by 1
  14. 2023NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity mapscited by 1
  15. 2025Minion Gated Recurrent Unit for Continual Learningcited by 1
  16. 2025Adaptive Neural Quantum States: A Recurrent Neural Network Perspectivecited by 1
  17. 2025Context-aware Sparse Spatiotemporal Learning for Event-based Visioncited by 1
  18. 2026Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum Statescited by 1
  19. 2021Advances in Electron Microscopy with Deep Learningcited by 0
  20. 2024TemporalAugmenter: An Ensemble Recurrent Based Deep Learning Approach for Signal Classificationcited by 0
  21. 2025Low-Resource Neural Machine Translation Using Recurrent Neural Networks and Transfer Learning: A Case Study on English-to-Igbocited by 0
  22. 2025Self-Supervised Event Representations: Towards Accurate, Real-Time Perception on SoC FPGAscited by 0
  23. 2025Unified Implementations of Recurrent Neural Networks in Multiple Deep Learning Frameworkscited by 0
  24. 2025M2RU: Memristive Minion Recurrent Unit for On-Chip Continual Learning at the Edgecited by 0
  25. 2026Rethinking Recurrent Neural Networks for Time Series Forecasting: A Reinforced Recurrent Encoder with Prediction-Oriented Proximal Policy Optimizationcited by 0
  26. 2026Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Modelscited by 0
  27. 2026End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge Distillationcited by 0
  28. 2026Train Short, Act Long: Multistability and the Horizon Independence of Recurrent Policiescited by 0