A Boxology of Design Patterns for Hybrid Learning and Reasoning Systems

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.

12 pages,55 references

References in corpus (4)

• Deep Learning: A Critical Appraisal
• Towards Deep Symbolic Reinforcement Learning
• Deep Learning for Ontology Reasoning
• Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

Cited by in corpus (3)

• Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• Moral Decision-Making in Medical Hybrid Intelligent Systems: A Team Design Patterns Approach to the Bias Mitigation and Data Sharing Design Problems
• Modular Design Patterns for Hybrid Actors