Solving nonograms using Neural Networks

TL;DR

This paper explores various methods, including neural networks, to solve nonogram puzzles, introducing a new dataset and demonstrating that combining neural networks with heuristic algorithms yields the best results.

Contribution

It is the first to use neural networks for solving nonograms and to combine them with heuristic algorithms, providing a new dataset and code for the community.

Findings

Neural network combined with heuristic algorithm performs best

Generated a public dataset for training neural networks on nonograms

No prior work used neural networks for nonogram solving

Abstract

Nonograms are logic puzzles in which cells in a grid must be colored or left blank according to the numbers that are located in its headers. In this study, we analyze different techniques to solve this type of logical problem using an Heuristic Algorithm, Genetic Algorithm, and Heuristic Algorithm with Neural Network. Furthermore, we generate a public dataset to train the neural networks. We published this dataset and the code of the algorithms. Combination of the heuristic algorithm with a neural network obtained the best results. From state of the art review, no previous works used neural network to solve nonograms, nor combined a network with other algorithms to accelerate the resolution process.