# Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks

arXiv: https://arxiv.org/abs/2602.03124 · HTML: https://mlsanity.com/paper/2602.03124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Compositional generalization through abstract representations in human and artificial neural networks](https://mlsanity.com/paper/2209.07431/) (2022)
- [A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines](https://mlsanity.com/paper/2202.08340/) (2022)
- [Learning Inductive Biases with Simple Neural Networks](https://mlsanity.com/paper/1802.02745/) (2018)
- [Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations](https://mlsanity.com/paper/2310.09612/) (2023)

## Abstract (arXiv)

Understanding how humans and machines learn from sparse data is central to cognitive science and machine learning. Using a species-fair design, we compare children and convolutional neural networks (CNNs) in a few-shot semi-supervised category learning task. Both learners are exposed to novel object categories under identical conditions. Learners receive mixtures of labeled and unlabeled exemplars while we vary supervision (1/3/6 labels), target feature (size, shape, pattern), and perceptual alignment (high/low). We find that children generalize rapidly from minimal labels but show strong feature-specific biases and sensitivity to alignment. CNNs show a different interaction profile: added supervision improves performance, but both alignment and feature structure moderate the impact additional supervision has on learning. These results show that human-model comparisons must be drawn under the right conditions, emphasizing interactions among supervision, feature structure, and alignment rather than overall accuracy.