mlsanityData to 7 Oct 2026

Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex

arXiv 1604.03640 ↗First posted 13 Apr 2016cs.LG cs.NEcited by 42

Not on the map. Why?

Abstract (arXiv)

We discuss relations between Residual Networks (ResNet), Recurrent Neural Networks (RNNs) and the primate visual cortex. We begin with the observation that a special type of shallow RNN is exactly equivalent to a very deep ResNet with weight sharing among the layers. A direct implementation of such a RNN, although having orders of magnitude fewer parameters, leads to a performance similar to the corresponding ResNet. We propose 1) a generalization of both RNN and ResNet architectures and 2) the conjecture that a class of moderately deep RNNs is a biologically-plausible model of the ventral stream in visual cortex. We demonstrate the effectiveness of the architectures by testing them on the CIFAR-10 and ImageNet dataset.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 9; 2023: 8; 2024: 2; 2025: 7; 2026: 2.

42 papers.

Sort:

By area:

  1. 2021Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networkscited by 108
  2. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 99
  3. 2021Encoding physics to learn reaction-diffusion processescited by 61
  4. 2021Adaptive Rational Activations to Boost Deep Reinforcement Learningcited by 23
  5. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  6. 2022The least-control principle for local learning at equilibriumcited by 16
  7. 2025Block-Recurrent Dynamics in Vision Transformerscited by 16
  8. 2021Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregationcited by 13
  9. 2023Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignmentcited by 13
  10. 2025Hierarchical Reasoning Models: Perspectives and Misconceptionscited by 13
  11. 2023Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?cited by 10
  12. 2025Better artificial intelligence does not mean better models of biologycited by 10
30 more
  1. 2021The Uncanny Similarity of Recurrence and Depthcited by 9
  2. 2022An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuitscited by 9
  3. 2023System identification of neural systems: If we got it right, would we know?cited by 9
  4. 2021Hard Encoding of Physics for Learning Spatiotemporal Dynamicscited by 8
  5. 2023Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levelscited by 6
  6. 2021TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNscited by 4
  7. 2022ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connectionscited by 4
  8. 2022Geometric and Topological Inference for Deep Representations of Complex Networkscited by 4
  9. 2022Entangled Residual Mappingscited by 4
  10. 2022Understanding Adversarial Robustness of Vision Transformers via Cauchy Problemcited by 4
  11. 2021Rethinking ResNets: Improved Stacking Strategies With High Order Schemescited by 3
  12. 2021Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorizationcited by 2
  13. 2021Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermaskscited by 2
  14. 2022The Mori-Zwanzig formulation of deep learningcited by 2
  15. 2023Multicoated and Folded Graph Neural Networks with Strong Lottery Ticketscited by 2
  16. 2024Deep Continuous Networkscited by 2
  17. 2021The Ikshana Hypothesis of Human Scene Understandingcited by 1
  18. 2023A Goal-Driven Approach to Systems Neurosciencecited by 1
  19. 2023On Tuning Neural ODE for Stability, Consistency and Faster Convergencecited by 1
  20. 2024Artificial Human Intelligence: The role of Humans in the Development of Next Generation AIcited by 1
  21. 2025Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospectscited by 1
  22. 2026Looped Transformers with Source-Centered State Evolutioncited by 1
  23. 2021Residual networks classify inputs based on their neural transient dynamicscited by 0
  24. 2021ItNet: iterative neural networks with small graphs for accurate, efficient and anytime semantic segmentationcited by 0
  25. 2022SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networkscited by 0
  26. 2022Are All Edges Necessary? A Unified Framework for Graph Purificationcited by 0
  27. 2025Traveling Waves Integrate Spatial Information Through Timecited by 0
  28. 2025Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separationcited by 0
  29. 2025Simulated Cortical Magnification Supports Self-Supervised Object Learningcited by 0
  30. 2026Scheduling Recursive Reasoning in Looped Transformerscited by 0