Deep Learning with Logical Constraints
It organizes existing research on combining logic and deep learning, which is incremental as it synthesizes prior work without introducing new methods.
This survey categorizes recent works that integrate logically specified background knowledge into neural models to improve performance, reduce data requirements, and ensure compliance for safety-critical applications.
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.