NeurASP: Embracing Neural Networks into Answer Set Programming
Abstract
We present NeurASP, a simple extension of answer set programs by embracing neural networks. By treating the neural network output as the probability distribution over atomic facts in answer set programs, NeurASP provides a simple and effective way to integrate sub-symbolic and symbolic computation. We demonstrate how NeurASP can make use of a pre-trained neural network in symbolic computation and how it can improve the neural network's perception result by applying symbolic reasoning in answer set programming. Also, NeurASP can be used to train a neural network better by training with ASP rules so that a neural network not only learns from implicit correlations from the data but also from the explicit complex semantic constraints expressed by the rules.
Cite
@article{arxiv.2307.07700,
title = {NeurASP: Embracing Neural Networks into Answer Set Programming},
author = {Zhun Yang and Adam Ishay and Joohyung Lee},
journal= {arXiv preprint arXiv:2307.07700},
year = {2023}
}
Comments
16 pages, 29th International Joint Conference on Artificial Intelligence (IJCAI 2020). arXiv admin note: substantial text overlap with arXiv:2009.10256