https://www.dagstuhl.de/21192

09. – 12. Mai 2021, Dagstuhl-Seminar 21192

Approaches and Applications of Inductive Programming

Organisatoren

Andrew Cropper (University of Oxford, GB)
Luc De Raedt (KU Leuven, BE)
Richard Evans (DeepMind – London, GB)
Ute Schmid (Universität Bamberg, DE)

Auskunft zu diesem Dagstuhl-Seminar erteilen

Susanne Bach-Bernhard zu administrativen Fragen

Michael Gerke zu wissenschaftlichen Fragen

Dokumente

Teilnehmerliste
Gemeinsame Dokumente
Dagstuhl-Seminar Wiki
Programm des Dagstuhl-Seminars (Hochladen)

(Zum Einloggen bitte persönliche DOOR-Zugangsdaten verwenden)

Motivation

Inductive programming addresses the problem of learning programs from incomplete specifications, typically from input/output examples. Researchers on this topic have backgrounds in diverse areas of computer science, namely in machine learning, artificial intelligence, declarative programming, program verification, and software engineering. Furthermore, inductive programming is of interest to researchers in cognitive science, working on computational models of inductive learning, and to researchers in education, especially in cognitive tutoring. A breakthrough from basic research to applications for the mass-market was achieved by applying inductive programming techniques to programming by examples support of end-users for Microsoft Excel (Flashfill).

This seminar is a continuation of Dagstuhl Seminars 13502, 15442, 17382, and 19202. In every installation, a specific topic has been in focus. The first focus was been on bringing together different areas of research and applications of inductive programming. The second focus was on the in-depth coverage of algorithmic methods and relations to cognitive modelling. The third focus was on application areas such as data cleansing, teaching programming, and interactive training. The fourth focus was exploring the potential of inductive programming for explainable artificial intelligence (XAI), especially combinations with (deep) neural networks and with data science.

Based on the results of the fourth seminar, the focus of this fifth seminar will be on inductive programming as a powerful approach for explainable artificial intelligence (`IP for XAI'). Since inductive programming is a highly expressive approach to interpretable machine learning which allows us to naturally combine reasoning and learning, it offers promising methods for explanation generation, especially in combination with (deep) neural networks and with data science. For many real-world applications, it is necessary or recommendable to involve the human as a teacher and judge for the machine-learned models. Therefore, a second focus of the seminar is to explore inductive programming in the context of new approaches to interactive machine learning and in relation to cognitive science research on human learning.

Expected outcomes of the seminar are:

  • Identifying the specific contributions of inductive programming to machine learning research and applications of machine learning, especially identifying problems for which inductive programming approaches are more suited than standard machine learning approaches, including deep learning. The focus is on possibilities of combining (deep) neural approaches and (symbolic) inductive programming, especially with respect to new approaches to the comprehensibility of machine-learned models and on explainable AI.
  • Discussing current applications of inductive programming in end-user programming and programming education and identifying further relevant areas of application.
  • Strengthening the relation of inductive programming and data science, especially with respect to data cleansing and data wrangling.
  • Establishing stronger relations between cognitive science research on inductive learning and inductive programming under the label of human-like computation and making use of cognitive principles in interactive machine learning to keep humans in the loop of decision making.

Motivation text license
  Creative Commons BY 3.0 DE
  Andrew Cropper, Luc De Raedt, Richard Evans, and Ute Schmid

Dagstuhl-Seminar Series

Classification

  • Artificial Intelligence
  • Human-Computer Interaction
  • Machine Learning

Keywords

  • Interpretable Machine Learning
  • Explainable Artificial Intelligence
  • Interactive Learning
  • Human-like Computing
  • Inductive Logic Programming

Dokumentation

In der Reihe Dagstuhl Reports werden alle Dagstuhl-Seminare und Dagstuhl-Perspektiven-Workshops dokumentiert. Die Organisatoren stellen zusammen mit dem Collector des Seminars einen Bericht zusammen, der die Beiträge der Autoren zusammenfasst und um eine Zusammenfassung ergänzt.

 

Download Übersichtsflyer (PDF).

Publikationen

Es besteht weiterhin die Möglichkeit, eine umfassende Kollektion begutachteter Arbeiten in der Reihe Dagstuhl Follow-Ups zu publizieren.

Dagstuhl's Impact

Bitte informieren Sie uns, wenn eine Veröffentlichung ausgehend von
Ihrem Seminar entsteht. Derartige Veröffentlichungen werden von uns in der Rubrik Dagstuhl's Impact separat aufgelistet  und im Erdgeschoss der Bibliothek präsentiert.