Combining neural and symbolic approaches to solve the Picasso problem: A first step

In this work we create a bridge between Convolutional Neural Networks and Answer Set Programming in order to tackle the known Picasso Problem in the automated detection of images. The basic idea is to first exploit the main features of the neural network approach for image recognition, and then to address the problem of identifying well-formed (not meshed up) images by means of explicit knowledge expressed by logical rules. Preliminary experiments suggest that the proposed approach is promising and can be considered as a first step in the direction of solving the Picasso Problem, as well as a witness of the benefits that can be obtained by the combination of a neural approach with a pure symbolic one.

Automated summary

This work establishes a connection between Convolutional Neural Networks and Answer Set Programming to address the Picasso Problem in image detection. By utilizing the neural network approach for image recognition and logical rules for identifying well-formed images, preliminary experiments show promising results in solving the Picasso Problem.