Few-Shot Induction of Generalized Logical Concepts via Human Guidance

Das, Mayukh and Ramanan, Nandini and Doppa, Janardhan Rao and Natarajan, Sriraam (2020) Few-Shot Induction of Generalized Logical Concepts via Human Guidance. Frontiers in Robotics and AI, 7. ISSN 2296-9144

[thumbnail of pubmed-zip/versions/2/package-entries/frobt-07-00122-r1/frobt-07-00122.pdf] Text
pubmed-zip/versions/2/package-entries/frobt-07-00122-r1/frobt-07-00122.pdf - Published Version

Download (1MB)

Abstract

We consider the problem of learning generalized first-order representations of concepts from a small number of examples. We augment an inductive logic programming learner with 2 novel contributions. First, we define a distance measure between candidate concept representations that improves the efficiency of search for target concept and generalization. Second, we leverage richer human inputs in the form of advice to improve the sample efficiency of learning. We prove that the proposed distance measure is semantically valid and use that to derive a PAC bound. Our experiments on diverse learning tasks demonstrate both the effectiveness and efficiency of our approach.

Item Type: Article
Subjects: West Bengal Archive > Mathematical Science
Depositing User: Unnamed user with email support@westbengalarchive.com
Date Deposited: 26 Jul 2024 07:04
Last Modified: 26 Jul 2024 07:04
URI: http://article.stmacademicwriting.com/id/eprint/1184

Actions (login required)

View Item
View Item