Teaching machines to learn by metaphors

Omer Levy*, Shaul Markovitch

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Humans have an uncanny ability to learn new concepts with very few examples. Cognitive theories have suggested that this is done by utilizing prior experience of related tasks. We propose to emulate this process in machines, by transforming new problems into old ones. These transformations are called metaphors. Obviously, the learner is not given a metaphor, but must acquire one through a learning process. We show that learning metaphors yield better results than existing transfer learning methods. Moreover, we argue that metaphors give a qualitative assessment of task relatedness.

Original languageEnglish
Title of host publicationAAAI-12 / IAAI-12 - Proceedings of the 26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference
Pages991-997
Number of pages7
StatePublished - 2012
Externally publishedYes
Event26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference, AAAI-12 / IAAI-12 - Toronto, ON, Canada
Duration: 22 Jul 201226 Jul 2012

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume2

Conference

Conference26th AAAI Conference on Artificial Intelligence and the 24th Innovative Applications of Artificial Intelligence Conference, AAAI-12 / IAAI-12
Country/TerritoryCanada
CityToronto, ON
Period22/07/1226/07/12

Fingerprint

Dive into the research topics of 'Teaching machines to learn by metaphors'. Together they form a unique fingerprint.

Cite this