NeurASP: Embracing Neural Networks into Answer Set Programming
NeurASP: Embracing Neural Networks into Answer Set Programming
复制标题
DOI：
10.24963/ijcai.2020/243
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Zhun Yang;Adam Ishay;Joohyung Lee
中科院分区：
文献类型：
--
作者：
Zhun Yang;Adam Ishay;Joohyung Lee
我们介绍神经拉斯，这是通过拥抱神经网络的简单扩展答案集程序。通过将神经网络输出视为答案集程序中原子事实的概率分布，Neurasp提供了一种简单有效的方法来整合亚符号和符号计算。我们演示了神经乳中的神经乳中如何利用符号计算中的预训练的神经网络，以及如何通过在答案集编程中应用符号推理来改善神经网络的感知结果。同样，神经乳头可以利用ASP规则来更好地训练神经网络，从而使神经网络不仅可以从数据中的隐式相关性中学习，还可以从规则表达的显式复杂语义约束中学习。
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 make use of ASP rules to train a neural network better 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.