# End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior

arXiv: https://arxiv.org/abs/2007.08723 · HTML: https://mlsanity.com/paper/2007.08723/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [On the Informativeness of Supervision Signals](https://mlsanity.com/paper/2211.01407/) (2022)
- [Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining](https://mlsanity.com/paper/2109.04652/) (2021)
- [Grounding Psychological Shape Space in Convolutional Neural Networks](https://mlsanity.com/paper/2111.08409/) (2021)
- [CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention](https://mlsanity.com/paper/2301.06216/) (2023)
- [A Rational Model of Dimension-reduced Human Categorization](https://mlsanity.com/paper/2305.14383/) (2023)
- [Cognitive Exoskeleton: Augmenting Human Cognition with an AI-Mediated Intelligent Visual Feedback](https://mlsanity.com/paper/2508.00846/) (2025)

## Abstract (arXiv)

Traditional models of category learning in psychology focus on representation at the category level as opposed to the stimulus level, even though the two are likely to interact. The stimulus representations employed in such models are either hand-designed by the experimenter, inferred circuitously from human judgments, or borrowed from pretrained deep neural networks that are themselves competing models of category learning. In this work, we extend classic prototype and exemplar models to learn both stimulus and category representations jointly from raw input. This new class of models can be parameterized by deep neural networks (DNN) and trained end-to-end. Following their namesakes, we refer to them as Deep Prototype Models, Deep Exemplar Models, and Deep Gaussian Mixture Models. Compared to typical DNNs, we find that their cognitively inspired counterparts both provide better intrinsic fit to human behavior and improve ground-truth classification.