Analogical mapping and inference in overlapping networks.

Munro, Paul and Peng, Yefei (2009) Analogical mapping and inference in overlapping networks. In: Analogy 09, 24 July 2009 - 27 July 2009, Sofia, Bulgaria.

Preview	PDF Primary Text Available under License : See the attached license file. Download (1MB) | Preview
	Plain Text (licence) Available under License : See the attached license file. Download (1kB)

Abstract

A method for training overlapping feed-forward networks on analogous tasks is extended and analyzed. The learning dynamics of simultaneous (interlaced) training of similar tasks interact at the shared connections of the networks. The output of one network in re-sponse to a stimulus to the other network can be interpreted as an analogical inference. In a similar fashion, the networks can be explicitly trained to map specific items in one domain to specifc items in the other domain. The method has been applied to spatial tasks in a simple environments and to tree structures.

---

Share

Citation/Export:	Select format... Citation - Text Citation - HTML Endnote BibTex Dublin Core OpenURL MARC (ISO 2709) METS MODS EP3 XML Reference Manager Refer
Social Networking:	Share |

---

Details

Item Type:	Conference or Workshop Item (Poster)
Status:	Published
Creators/Authors:	Creators Email Pitt Username ORCID Munro, Paul pwm@pitt.edu PWM Peng, Yefei
Date:	2009
Date Type:	Publication
Access Restriction:	No restriction; Release the ETD for access worldwide immediately.
Publisher:	New Bulgarian University Press.
Place of Publication:	Bulgaria
Page Range:	473 - 479
Event Title:	Analogy 09
Event Dates:	24 July 2009 - 27 July 2009
Event Type:	Conference
Institution:	University of Pittsburgh
Schools and Programs:	School of Information Sciences > Information Science
Refereed:	Yes
Editors:	Editors Email Pitt Username ORCID Kokinov, B UNSPECIFIED UNSPECIFIED UNSPECIFIED Holyoak, K UNSPECIFIED UNSPECIFIED UNSPECIFIED Gentner, D UNSPECIFIED UNSPECIFIED UNSPECIFIED
Date Deposited:	29 Jun 2012 20:05
Last Modified:	16 Jul 2024 10:55
URI:	http://d-scholarship.pitt.edu/id/eprint/12631

---

Metrics

Monthly Views for the past 3 years

Plum Analytics

---

Actions (login required)

View Item