Deep Learning with Logical Constraints
Deep Learning with Logical Constraints
复制标题
DOI：
10.24963/ijcai.2022/767
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Eleonora Giunchiglia;Mihaela C. Stoian;Thomas Lukasiewicz
中科院分区：
文献类型：
--
作者：
Eleonora Giunchiglia;Mihaela C. Stoian;Thomas Lukasiewicz
近年来，人们对利用逻辑指定的背景知识越来越感兴趣，以获得神经模型(i)具有更好的性能，（ii）能够从更少的数据中学习，和/或（iii）保证与背景知识本身兼容，例如，用于安全关键应用。在本次调查中，我们追溯了这些作品，并根据(i)它们用来表达背景知识的逻辑语言和（ii）它们实现的目标对它们进行了分类。
In recent years, there has been an increasing interest in exploiting logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e.g., for safety-critical applications. In this survey, we retrace such works and categorize them based on (i) the logical language that they use to express the background knowledge and (ii) the goals that they achieve.