Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

Self-supervised Learning of Concepts by Single Units and "Weakly Local" Representations

Munro, Paul (1988) Self-supervised Learning of Concepts by Single Units and "Weakly Local" Representations. Technical Report. School of Library and Information Science, University of Pittsburgh, Pittsburgh, PA.

[img] Plain Text (licence)
Available under License : See the attached license file.
Download (1kB)

Abstract

A mathematical system, self-supervised learning (SSL) is presented that describes a form of learning high order concept units (C-units) that learn to become sensitive to categories of stimuli associated by finding some feature (the concept)that they share. Implicit in the SSL model is the assumption that each C-unit receives input from at least two information streams or "banks". under SSL, each C-unit becomes very selective across one of the streams, the training bank; that is, patterns in the training bank are strongly filtered by the C-unit such that nearly all of them are ignored, save one, or a few. The preferred stimulus pattern in the training bank serves as a "seed" for concept formation, as an associative process causes the stimulus in the world. The possibility that linguistics information may provide seed stimuli suggest an approach via SSL for understanding the role of language in concept formation.

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Monograph (Technical Report)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Munro, Paulpwm@pitt.eduPWM
Monograph Type: Technical Report
Date: 1988
Date Type: Publication
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Publisher: School of Library and Information Science, University of Pittsburgh
Place of Publication: Pittsburgh, PA
Institution: University of Pittsburgh
Department: School of Library and Information Science
Schools and Programs: School of Information Sciences > Library and Information Science
Refereed: No
University of Pittsburgh Series: iSchool Research Report Series
Other ID: LIS003/IS88003
Date Deposited: 11 Apr 2013 17:29
Last Modified: 01 Nov 2017 14:02
URI: http://d-scholarship.pitt.edu/id/eprint/18276

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item