# Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization

arXiv: https://arxiv.org/abs/2111.07898 · HTML: https://mlsanity.com/paper/2111.07898/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 15 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Residual Connections Encourage Iterative Inference](https://mlsanity.com/paper/1710.04773/) (2017)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex](https://mlsanity.com/paper/1604.03640/) (2016)
- [Task-Driven Convolutional Recurrent Models of the Visual System](https://mlsanity.com/paper/1807.00053/) (2018)
- [Going in circles is the way forward: the role of recurrence in visual inference](https://mlsanity.com/paper/2003.12128/) (2020)
- [A Probabilistic Theory of Deep Learning](https://mlsanity.com/paper/1504.00641/) (2015)
- [How recurrent networks implement contextual processing in sentiment analysis](https://mlsanity.com/paper/2004.08013/) (2020)
- [Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders](https://mlsanity.com/paper/1907.08831/) (2019)

## Built on by (most cited first, 2 of 2)

- [Characterising representation dynamics in recurrent neural networks for object recognition](https://mlsanity.com/paper/2308.12435/) (2023)
- [Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks](https://mlsanity.com/paper/2310.04741/) (2023)

## Abstract (arXiv)

Recurrent neural networks (RNNs) have been shown to perform better than feedforward architectures in visual object categorization tasks, especially in challenging conditions such as cluttered images. However, little is known about the exact computational role of recurrent information flow in these conditions. Here we test RNNs trained for object categorization on the hypothesis that recurrence iteratively aids object categorization via the communication of category-orthogonal auxiliary variables (the location, orientation, and scale of the object). Using diagnostic linear readouts, we find that: (a) information about auxiliary variables increases across time in all network layers, (b) this information is indeed present in the recurrent information flow, and (c) its manipulation significantly affects task performance. These observations confirm the hypothesis that category-orthogonal auxiliary variable information is conveyed through recurrent connectivity and is used to optimize category inference in cluttered environments.