A Boxology of Design Patterns forHybrid Learningand Reasoning Systems

2019/01/01 by Frank van Harmelen, Annette ten Teije
Computer Science · Engineering · #Advanced Database Systems and Queries #Artificial intelligence #Computer science #Data Mining Algorithms and Applications #Data science #Engineering #Engineering design process #Knowledge representation and reasoning #Ontology #Process (computing) #Programming language #Representation (politics) #Semantic Web and Ontologies #Set (abstract data type) #Software #Software design pattern #Software engineering #Variety (cybernetics) #cs.AI

paper · pdf · doi:10.13052/jwe1540-9589.18133

published as Journal of Web Engineering, Vol. 18 1-3, pgs. 97-124, 2019 · 12 pages,55 references

openalex publication_date 2019/01/01 · arxiv created 2019/05/29 · arxiv updated 2019/05/30 · openalex created_date 2019/06/07 · openalex updated_date 2026/08/05

Abstract

We propose a set of compositional design patterns to describe a large variety of systems that combine statistical techniques from machine learning with symbolic techniques from knowledge representation. As in other areas of computer science (knowledge engineering, software engineering, ontology engineering, process mining and others), such design patterns help to systematize the literature, clarify which combinations of techniques serve which purposes, and encourage re-use of software components. We have validated our set of compositional design patterns against a large body of recent literature.

Citations

• Clustering by Compression
• Building Machines That Learn and Think Like People
• Deep Learning for Ontology Reasoning
• Differentiable Learning of Logical Rules for Knowledge Base Reasoning
• Explaining Trained Neural Networks with Semantic Web Technologies: First Steps
• A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• Deep Learning: A Critical Appraisal
• Knowledge-based Transfer Learning Explanation
• Reasoning over RDF Knowledge Bases using Deep Learning