# The Representational Status of Deep Learning Models

arXiv: https://arxiv.org/abs/2303.12032 · HTML: https://mlsanity.com/paper/2303.12032/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 105 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 25 of 25)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [Understanding artificial intelligence ethics and safety](https://mlsanity.com/paper/1906.05684/) (2019)
- [A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations](https://mlsanity.com/paper/1805.07039/) (2018)
- [Towards falsifiable interpretability research](https://mlsanity.com/paper/2010.12016/) (2020)
- [Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition](https://mlsanity.com/paper/1406.3284/) (2014)
- [Why AI is Harder Than We Think](https://mlsanity.com/paper/2104.12871/) (2021)
- [A Survey of Deep Learning for Scientific Discovery](https://mlsanity.com/paper/2003.11755/) (2020)
- [Humans can decipher adversarial images](https://mlsanity.com/paper/1809.04120/) (2018)
- [Overinterpretation reveals image classification model pathologies](https://mlsanity.com/paper/2003.08907/) (2020)
- [Generative models as parsimonious descriptions of sensorimotor loops](https://mlsanity.com/paper/1904.12937/) (2019)
- [Deep Learning Opacity in Scientific Discovery](https://mlsanity.com/paper/2206.00520/) (2022)
- [A Philosophical Understanding of Representation for Neuroscience](https://mlsanity.com/paper/2102.06592/) (2021)

## Built on by (most cited first, 1 of 1)

- [DNNs, Dataset Statistics, and Correlation Functions](https://mlsanity.com/paper/2511.21715/) (2025)

## Abstract (arXiv)

This paper aims to clarify the representational status of Deep Learning Models (DLMs). While commonly referred to as 'representations', what this entails is ambiguous due to a conflation of functional and relational conceptions of representation. This paper argues that while DLMs represent their targets in a relational sense, in general, we have no good reason to believe that DLMs encode locally semantically decomposable representations of their targets. That is, the representational capacity these models have is largely global, rather than decomposable into stable, local subrepresentations. This result has immediate implications for explainable AI (XAI) and directs attention toward exploring the global relational nature of deep learning representations and their relationship both to models more generally to understand their potential role in future scientific inquiry.