CaltechAUTHORS
  A Caltech Library Service

The Scheduling Problem in Learning From Hints

Çataltepe, Zehra (1994) The Scheduling Problem in Learning From Hints. Computer Science Technical Reports, 94-09. California Institute of Technology , Pasadena, CA. (Unpublished) http://resolver.caltech.edu/CaltechCSTR:1994.cs-tr-94-09

[img]
Preview
PDF - Submitted Version
See Usage Policy.

2284Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechCSTR:1994.cs-tr-94-09

Abstract

Any information about the function to be learned is called a hint. Learning from hints is a generalization of learning from examples. In this paradigm, hints are expressed by their examples and then taught to a learning-from-examples system. In general, using other hints in addition to the examples of the function, improves the generalization performance. The scheduling problem in learning from hints is deciding which hint to teach at which time during training. Over- or under- emphasizing a hint may render it useless, making scheduling very important. Fixed and adaptive schedules are two types of schedules that are discussed. Adaptive minimization is a general adaptive schedule that uses an estimate of generalization error in terms of errors on hints. When such an estimate is available, it can also be optimized by means of directly descending on it. An estimate may be used to decide on when to stop training, too. A method to find an estimate incorporating the errors on invariance hints, and simulation results on this estimate, are presented. Two computer programs that provide a learning-from-hints environment and improvements on them are discussed.


Item Type:Report or Paper (Technical Report)
Related URLs:
URLURL TypeDescription
http://resolver.caltech.edu/CaltechTHESIS:03272012-100501462Related ItemAuthor Master's thesis in CaltechTHESIS
Additional Information:© Zehra Cataltepe 1994, California Institute of Technology. Many thanks to my academic and research advisor, Yaser S. Abu-Mostafa, for his guidance, support and advice. Thanks to Eric T. Bax, Bahadir Erimli, and Ayhan Irfanoglu, for proofreading and suggestions. Any overseen mistakes are solely mine. Thanks to the members of the Learning System Group - Eric T. Bax, Joe Sill, and Xubo Song - for valuable discussions. And finally, thanks to my mother and father, my beloved husband Tanju, and my brothers Ahmet and Rifat, to all my friends, and whomever I forgot to thank. This research was supported by the AFOSR under grant number F49620-92-J-0398.
Group:Computer Science Technical Reports
Funders:
Funding AgencyGrant Number
Air Force Office of Scientific Research (AFOSR)F49620-92-J-0398
DOI:10.7907/Z93T9F7B
Record Number:CaltechCSTR:1994.cs-tr-94-09
Persistent URL:http://resolver.caltech.edu/CaltechCSTR:1994.cs-tr-94-09
Usage Policy:You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.
ID Code:26788
Collection:CaltechCSTR
Deposited By: Imported from CaltechCSTR
Deposited On:25 Apr 2001
Last Modified:23 May 2017 18:35

Repository Staff Only: item control page