# Going in circles is the way forward: the role of recurrence in visual inference

arXiv: https://arxiv.org/abs/2003.12128 · HTML: https://mlsanity.com/paper/2003.12128/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2020.

## Built on by (most cited first, 19 of 19)

- [Zamba: A Compact 7B SSM Hybrid Model](https://mlsanity.com/paper/2405.16712/) (2024)
- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [GPTEval: A Survey on Assessments of ChatGPT and GPT-4](https://mlsanity.com/paper/2308.12488/) (2023)
- [Data-driven emergence of convolutional structure in neural networks](https://mlsanity.com/paper/2202.00565/) (2022)
- [Hybrid Predictive Coding: Inferring, Fast and Slow](https://mlsanity.com/paper/2204.02169/) (2022)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?](https://mlsanity.com/paper/2510.24709/) (2025)
- [The least-control principle for local learning at equilibrium](https://mlsanity.com/paper/2207.01332/) (2022)
- [Layer Folding: Neural Network Depth Reduction using Activation Linearization](https://mlsanity.com/paper/2106.09309/) (2021)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?](https://mlsanity.com/paper/2305.17023/) (2023)
- [Better artificial intelligence does not mean better models of biology](https://mlsanity.com/paper/2504.16940/) (2025)
- [Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition](https://mlsanity.com/paper/2112.12175/) (2021)
- [Bio-Inspired, Task-Free Continual Learning through Activity Regularization](https://mlsanity.com/paper/2212.04316/) (2022)
- [Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence](https://mlsanity.com/paper/2103.13512/) (2021)
- [Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition](https://mlsanity.com/paper/2110.04954/) (2021)
- [Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization](https://mlsanity.com/paper/2111.07898/) (2021)
- [Characterising representation dynamics in recurrent neural networks for object recognition](https://mlsanity.com/paper/2308.12435/) (2023)
- [Early Exiting Predictive Coding Neural Networks for Edge AI](https://mlsanity.com/paper/2309.02022/) (2023)

## Abstract (arXiv)

Biological visual systems exhibit abundant recurrent connectivity. State-of-the-art neural network models for visual recognition, by contrast, rely heavily or exclusively on feedforward computation. Any finite-time recurrent neural network (RNN) can be unrolled along time to yield an equivalent feedforward neural network (FNN). This important insight suggests that computational neuroscientists may not need to engage recurrent computation, and that computer-vision engineers may be limiting themselves to a special case of FNN if they build recurrent models. Here we argue, to the contrary, that FNNs are a special case of RNNs and that computational neuroscientists and engineers should engage recurrence to understand how brains and machines can (1) achieve greater and more flexible computational depth, (2) compress complex computations into limited hardware, (3) integrate priors and priorities into visual inference through expectation and attention, (4) exploit sequential dependencies in their data for better inference and prediction, and (5) leverage the power of iterative computation.