# Extracting low-dimensional psychological representations from convolutional neural networks

arXiv: https://arxiv.org/abs/2005.14363 · HTML: https://mlsanity.com/paper/2005.14363/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2020.

## Built on by (most cited first, 16 of 16)

- [Human-like object concept representations emerge naturally in multimodal large language models](https://mlsanity.com/paper/2407.01067/) (2024)
- [Words are all you need? Language as an approximation for human similarity judgments](https://mlsanity.com/paper/2206.04105/) (2022)
- [On the Informativeness of Supervision Signals](https://mlsanity.com/paper/2211.01407/) (2022)
- [Predicting Human Similarity Judgments Using Large Language Models](https://mlsanity.com/paper/2202.04728/) (2022)
- [CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations](https://mlsanity.com/paper/2404.16482/) (2024)
- [The Universal Law of Generalization Holds for Naturalistic Stimuli](https://mlsanity.com/paper/2306.08564/) (2023)
- [Divergences in Color Perception between Deep Neural Networks and Humans](https://mlsanity.com/paper/2309.05809/) (2023)
- [Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning](https://mlsanity.com/paper/2403.07078/) (2024)
- [Algebras of actions in an agent's representations of the world](https://mlsanity.com/paper/2310.01536/) (2023)
- [Grounding Psychological Shape Space in Convolutional Neural Networks](https://mlsanity.com/paper/2111.08409/) (2021)
- [A Rational Model of Dimension-reduced Human Categorization](https://mlsanity.com/paper/2305.14383/) (2023)
- [Face processing emerges from object-trained convolutional neural networks](https://mlsanity.com/paper/2405.18800/) (2024)
- [Explaining Human Comparisons using Alignment-Importance Heatmaps](https://mlsanity.com/paper/2409.16292/) (2024)
- [Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Model](https://mlsanity.com/paper/2503.04842/) (2025)
- [Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in Bitexts](https://mlsanity.com/paper/2603.19924/) (2026)
- [Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks](https://mlsanity.com/paper/2606.10972/) (2026)

## Abstract (arXiv)

Deep neural networks are increasingly being used in cognitive modeling as a means of deriving representations for complex stimuli such as images. While the predictive power of these networks is high, it is often not clear whether they also offer useful explanations of the task at hand. Convolutional neural network representations have been shown to be predictive of human similarity judgments for images after appropriate adaptation. However, these high-dimensional representations are difficult to interpret. Here we present a method for reducing these representations to a low-dimensional space which is still predictive of similarity judgments. We show that these low-dimensional representations also provide insightful explanations of factors underlying human similarity judgments.