Approaches and Applications of Inductive Programming (Dagstuhl Seminar 21192)

Abstract

In this report the program and the outcomes of Dagstuhl Seminar 21192 Approaches and Applications of Inductive Programming is documented. The goal of inductive programming (IP) is to induce computer programs from data, typically input/output examples of a desired program. IP interests researchers from many areas of computer science, including machine learning, automated reasoning, program verification, and software engineering. Furthermore, IP contributes to research outside computer science, notably in cognitive science, where IP can help build models of human inductive learning and contribute methods for intelligent tutor systems. Building on the success of previous IP Dagstuhl seminars (13502, 15442, 17382, and 19202), the goal of this new edition of the seminar is to focus on IP methods which integrate learning and reasoning, scaling up IP methods to be applicable to more complex real world problems, and to further explore the potential of IP for explainable artificial intelligence (XAI), especially for interactive learning. The extended abstracts included in this report show recent advances in IP research. The included short report of the outcome of the discussion sessions additionally point out interesting interrelation between different aspects and possible new directions for IP.