mlsanityData to 7 Oct 2026

A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks

arXiv 1907.02649 ↗First posted 5 Jul 2019cs.LG cs.NE q-bio.NCcited by 37

Not on the map. Why?

Abstract (arXiv)

We present a framework for compactly summarizing many recent results in efficient and/or biologically plausible online training of recurrent neural networks (RNN). The framework organizes algorithms according to several criteria: (a) past vs. future facing, (b) tensor structure, (c) stochastic vs. deterministic, and (d) closed form vs. numerical. These axes reveal latent conceptual connections among several recent advances in online learning. Furthermore, we provide novel mathematical intuitions for their degree of success. Testing various algorithms on two synthetic tasks shows that performances cluster according to our criteria. Although a similar clustering is also observed for gradient alignment, alignment with exact methods does not alone explain ultimate performance, especially for stochastic algorithms. This suggests the need for better comparison metrics.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 3; 2023: 10; 2024: 8; 2025: 3; 2026: 5.

37 papers.

Sort:

By area:

  1. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  2. 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
  3. 2022Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagationcited by 26
  4. 2023Online learning of long-range dependenciescited by 25
  5. 2021Online Variational Filtering and Parameter Learningcited by 19
  6. 2023Latent State Models of Training Dynamicscited by 15
  7. 2023How connectivity structure shapes rich and lazy learning in neural circuitscited by 15
  8. 2021How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspectivecited by 13
  9. 2023Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradientcited by 11
  10. 2024Backpropagation through space, time, and the braincited by 10
  11. 2024Real-Time Recurrent Learning using Trace Units in Reinforcement Learningcited by 10
  12. 2023Persistent learning signals and working memory without continuous attractorscited by 6
25 more
  1. 2023Real-Time Recurrent Reinforcement Learningcited by 6
  2. 2023SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networkscited by 6
  3. 2022Distinguishing Learning Rules with Brain Machine Interfacescited by 5
  4. 2023Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobianscited by 5
  5. 2021Online hyperparameter optimization by real-time recurrent learningcited by 4
  6. 2021Prediction of the Position of External Markers Using a Recurrent Neural Network Trained With Unbiased Online Recurrent Optimization for Safe Lung Cancer Radiotherapycited by 4
  7. 2022Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rulescited by 3
  8. 2023Efficient Real Time Recurrent Learning through combined activity and parameter sparsitycited by 3
  9. 2024LongSSM: On the Length Extension of State-space Models in Language Modellingcited by 3
  10. 2025Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learningcited by 3
  11. 2021Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piececited by 2
  12. 2023Online Evolutionary Neural Architecture Search for Multivariate Non-Stationary Time Series Forecastingcited by 2
  13. 2024Real-time respiratory motion forecasting with online learning of recurrent neural networks for accurate targeting in externally guided radiotherapycited by 1
  14. 2024A Unified Framework for Neural Computation and Learning Over Timecited by 1
  15. 2025Can Biologically Plausible Temporal Credit Assignment Rules Match BPTT for Neural Similarity? E-prop as an Examplecited by 1
  16. 2026Three factor delay learning rules for spiking neural networkscited by 1
  17. 2021Neko: a Library for Exploring Neuromorphic Learning Rulescited by 0
  18. 2024BP(λ): Online Learning via Synthetic Gradientscited by 0
  19. 2024Nature-Inspired Local Propagationcited by 0
  20. 2024Frame forecasting in cine MRI using the PCA respiratory motion model: comparing recurrent neural networks trained online and transformerscited by 0
  21. 2025A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networkscited by 0
  22. 2026Adaptive Control in Autonomous Driving via Real-Time Recurrent RLcited by 0
  23. 2026Learning Long-Range Dependencies with Temporal Predictive Codingcited by 0
  24. 2026Massive Redundancy in Gradient Transport Enables Sparse Online Learningcited by 0
  25. 2026Center-Manifold Reduction of Learning at Bifurcations: Interference and Rich Learning in Recurrent Neural Networkscited by 0