Semi-Supervised Learning using Differentiable Reasoning

Research output: Contribution to JournalArticleAcademicpeer-review

26 Downloads (Pure)

Abstract

We introduce Differentiable Reasoning (DR), a novel semi-supervised learning technique which uses relational background knowledge to benefit from unlabeled data. We apply it to the Semantic Image Interpretation (SII) task and show that background knowledge provides significant improvement. We find that there is a strong but interesting imbalance between the contributions of updates from Modus Ponens (MP) and its logical equivalent Modus Tollens (MT) to the learning process, suggesting that our approach is very sensitive to a phenomenon called the Raven Paradox. We propose a solution to overcome this situation.
Original languageEnglish
Pages (from-to)633-651
Number of pages19
JournalJournal of Applied Logic
Volume6
Issue number4
Publication statusPublished - Jun 2019

Bibliographical note

Special Issue: Neural-Symbolic Learning and Reasoning (NeSy'18). ISBN 9781848903067

Fingerprint Dive into the research topics of 'Semi-Supervised Learning using Differentiable Reasoning'. Together they form a unique fingerprint.

Cite this