# Solving Raven's Progressive Matrices with Neural Networks

arXiv: https://arxiv.org/abs/2002.01646 · HTML: https://mlsanity.com/paper/2002.01646/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2203.04571/) (2022)
- [Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices](https://mlsanity.com/paper/2201.12382/) (2022)
- [Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization](https://mlsanity.com/paper/2107.12580/) (2021)
- [Effective Abstract Reasoning with Dual-Contrast Network](https://mlsanity.com/paper/2205.13720/) (2022)
- [The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models](https://mlsanity.com/paper/2401.12117/) (2024)
- [Evaluating Understanding on Conceptual Abstraction Benchmarks](https://mlsanity.com/paper/2206.14187/) (2022)
- [Unsupervised Abstract Reasoning for Raven's Problem Matrices](https://mlsanity.com/paper/2109.10011/) (2021)
- [Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices](https://mlsanity.com/paper/2303.11730/) (2023)
- [Factorizers for Distributed Sparse Block Codes](https://mlsanity.com/paper/2303.13957/) (2023)
- [Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction](https://mlsanity.com/paper/2302.04238/) (2023)
- [Naive Few-Shot Learning: Uncovering the fluid intelligence of machines](https://mlsanity.com/paper/2205.12013/) (2022)
- [Zero-Episode Few-Shot Contrastive Predictive Coding: Solving intelligence tests without prior training](https://mlsanity.com/paper/2205.01924/) (2022)

## Abstract (arXiv)

Raven's Progressive Matrices (RPM) have been widely used for Intelligence Quotient (IQ) test of humans. In this paper, we aim to solve RPM with neural networks in both supervised and unsupervised manners. First, we investigate strategies to reduce over-fitting in supervised learning. We suggest the use of a neural network with deep layers and pre-training on large-scale datasets to improve model generalization. Experiments on the RAVEN dataset show that the overall accuracy of our supervised approach surpasses human-level performance. Second, as an intelligent agent requires to automatically learn new skills to solve new problems, we propose the first unsupervised method, Multilabel Classification with Pseudo Target (MCPT), for RPM problems. Based on the design of the pseudo target, MCPT converts the unsupervised learning problem to a supervised task. Experiments show that MCPT doubles the testing accuracy of random guessing e.g. 28.50% vs. 12.5%. Finally, we discuss the problem of solving RPM with unsupervised and explainable strategies in the future.