Work

Deep Learning with Logical Constraints

Year: 2022

Type: conference-paper

Abstract: 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.

Source: International Joint Conference on Artificial Intelligence

DOI: 10.24963/ijcai.2022/767

Authors: Eleonora Giunchiglia, Mihaela Catalina Stoian, Thomas Lukasiewicz

Institutions: University of Oxford, TU Wien

Language: English

Topic: Logic, Reasoning, and Knowledge

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: Alan Turing Institute, DeepMind, AXA Research Fund, Engineering and Physical Sciences Research Council