Skip to content

Information for students, faculty and staff regarding COVID-19. (Updated: 22 February 2021)

printicon

A boxology of design patterns for systems that learn and reason

Fri
12
Mar
Time Friday 12 March, 2021 at 12:15 - 13:00
Place Online via Zoom

The combination of data-driven techniques from machine learning with symbolic techniques from knowledge representation is recognized as one of the grand challenges of modern AI. 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.

To participate in the seminar #frAIday, please register here. We will send you a link to the Zoom event. Please note that you don't have to register for each event.

Event type: Lecture

Frank van Harmelen, Professor in Knowledge Representation and Reasoning in the Computer Science department (Faculty of Science) at Vrije Universiteit, Amsterdam.