# A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoning

arXiv: https://arxiv.org/abs/2403.05641 · HTML: https://mlsanity.com/paper/2403.05641/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 8 Mar 2024.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks](https://mlsanity.com/paper/2009.11848/) (2020)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [What Can Neural Networks Reason About?](https://mlsanity.com/paper/1905.13211/) (2019)
- [Are Disentangled Representations Helpful for Abstract Visual Reasoning?](https://mlsanity.com/paper/1905.12506/) (2019)
- [Neural Algorithmic Reasoning](https://mlsanity.com/paper/2105.02761/) (2021)
- [Stratified Rule-Aware Network for Abstract Visual Reasoning](https://mlsanity.com/paper/2002.06838/) (2020)
- [A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2203.04571/) (2022)
- [The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning](https://mlsanity.com/paper/2007.04212/) (2020)
- [Scale-Localized Abstract Reasoning](https://mlsanity.com/paper/2009.09405/) (2020)
- [Neural Algorithmic Reasoning with Causal Regularisation](https://mlsanity.com/paper/2302.10258/) (2023)
- [Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations](https://mlsanity.com/paper/1811.04784/) (2018)
- [On Neural Architecture Inductive Biases for Relational Tasks](https://mlsanity.com/paper/2206.05056/) (2022)
- [Multi-Label Contrastive Learning for Abstract Visual Reasoning](https://mlsanity.com/paper/2012.01944/) (2020)
- [Solving Raven's Progressive Matrices with Multi-Layer Relation Networks](https://mlsanity.com/paper/2003.11608/) (2020)
- [A Memory-Augmented Neural Network Model of Abstract Rule Learning](https://mlsanity.com/paper/2012.07172/) (2020)
- [Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction](https://mlsanity.com/paper/2302.04238/) (2023)
- [A model of cortical cognitive function using hierarchical interactions of gating matrices in internal agents coding relational representations](https://mlsanity.com/paper/1809.08203/) (2018)

## Abstract (arXiv)

A hallmark of human intelligence is the ability to infer abstract rules from limited experience and apply these rules to unfamiliar situations. This capacity is widely studied in the visual domain using the Raven's Progressive Matrices. Recent advances in deep learning have led to multiple artificial neural network models matching or even surpassing human performance. However, while humans can identify and express the rule underlying these tasks with little to no exposure, contemporary neural networks often rely on massive pattern-based training and cannot express or extrapolate the rule inferred from the task. Furthermore, most Raven's Progressive Matrices or Raven-like tasks used for neural network training used symbolic representations, whereas humans can flexibly switch between symbolic and continuous perceptual representations. In this work, we present an algorithmic approach to rule detection and application using feature detection, affine transformation estimation and search. We applied our model to a simplified Raven's Progressive Matrices task, previously designed for behavioral testing and neuroimaging in humans. The model exhibited one-shot learning and achieved near human-level performance in the symbolic reasoning condition of the simplified task. Furthermore, the model can express the relationships discovered and generate multi-step predictions in accordance with the underlying rule. Finally, the model can reason using continuous patterns. We discuss our results and their relevance to studying abstract reasoning in humans, as well as their implications for improving intelligent machines.