# Learning Inductive Biases with Simple Neural Networks

arXiv: https://arxiv.org/abs/1802.02745 · HTML: https://mlsanity.com/paper/1802.02745/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2018.

## Built on by (most cited first, 9 of 9)

- [POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples](https://mlsanity.com/paper/2206.04679/) (2022)
- [Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers](https://mlsanity.com/paper/2106.13122/) (2021)
- [A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines](https://mlsanity.com/paper/2202.08340/) (2022)
- [Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization](https://mlsanity.com/paper/2311.06224/) (2023)
- [EGR: Equivariant Graph Refinement and Assessment of 3D Protein Complex Structures](https://mlsanity.com/paper/2205.10390/) (2022)
- [Inductive Attention for Video Action Anticipation](https://mlsanity.com/paper/2212.08830/) (2022)
- [Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks](https://mlsanity.com/paper/2602.03124/) (2026)
- [Understanding Goal Generalisation in Sequential Reinforcement Learning](https://mlsanity.com/paper/2605.23565/) (2026)
- [The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer](https://mlsanity.com/paper/2610.03827/) (2026)

## Abstract (arXiv)

People use rich prior knowledge about the world in order to efficiently learn new concepts. These priors - also known as "inductive biases" - pertain to the space of internal models considered by a learner, and they help the learner make inferences that go beyond the observed data. A recent study found that deep neural networks optimized for object recognition develop the shape bias (Ritter et al., 2017), an inductive bias possessed by children that plays an important role in early word learning. However, these networks use unrealistically large quantities of training data, and the conditions required for these biases to develop are not well understood. Moreover, it is unclear how the learning dynamics of these networks relate to developmental processes in childhood. We investigate the development and influence of the shape bias in neural networks using controlled datasets of abstract patterns and synthetic images, allowing us to systematically vary the quantity and form of the experience provided to the learning algorithms. We find that simple neural networks develop a shape bias after seeing as few as 3 examples of 4 object categories. The development of these biases predicts the onset of vocabulary acceleration in our networks, consistent with the developmental process in children.