Machine Learning of Inductive Bias [electronic resource] /
This book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias.
Main Authors: | , |
---|---|
Format: | Texto biblioteca |
Language: | eng |
Published: |
Boston, MA : Springer US,
1986
|
Subjects: | Computer science., Artificial intelligence., Computer Science., Artificial Intelligence (incl. Robotics)., |
Online Access: | http://dx.doi.org/10.1007/978-1-4613-2283-2 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
KOHA-OAI-TEST:176753 |
---|---|
record_format |
koha |
spelling |
KOHA-OAI-TEST:1767532018-07-30T22:55:24ZMachine Learning of Inductive Bias [electronic resource] / Utgoff, Paul E. author. SpringerLink (Online service) textBoston, MA : Springer US,1986.engThis book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias.1 Introduction -- 1.1 Machine Learning -- 1.2 Learning Concepts from Examples -- 1.3 Role of Bias in Concept Learning -- 1.4 Kinds of Bias -- 1.5 Origin of Bias -- 1.6 Learning to Learn -- 1.7 The New-Term Problem -- 1.8 Guide to Remaining Chapters -- 2 Related Work -- 2.1 Learning Programs that use a Static Bias -- 2.2 Learning Programs that use a Dynamic Bias -- 3 Searching for a Better Bias -- 3.1 Simplifications -- 3.2 The RTA Method for Shifting Bias -- 4 LEX and STABB -- 4.1 LEX: A Program that Learns from Experimentation -- 4.2 STABB: a Program that Shifts Bias -- 5 Least Disjunction -- 5.1 Procedure -- 5.2 Requirements -- 5.3 Experiments -- 5.4 Example Trace -- 5.5 Discussion -- 6 Constraint Back-Propagation -- 6.1 Procedure -- 6.2 Requirements -- 6.3 Experiments -- 6.4 Example Trace -- 6.5 Discussion -- 7 Conclusion -- 7.1 Summary -- 7.2 Results -- 7.3 Issues -- 7.4 Further Work -- Appendix A: Lisp Code -- A.1 STABB -- A.2 Grammar -- A.3 Intersection -- A.4 Match -- A.5 Operators -- A.6 Utilities.This book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias.Computer science.Artificial intelligence.Computer Science.Artificial Intelligence (incl. Robotics).Springer eBookshttp://dx.doi.org/10.1007/978-1-4613-2283-2URN:ISBN:9781461322832 |
institution |
COLPOS |
collection |
Koha |
country |
México |
countrycode |
MX |
component |
Bibliográfico |
access |
En linea En linea |
databasecode |
cat-colpos |
tag |
biblioteca |
region |
America del Norte |
libraryname |
Departamento de documentación y biblioteca de COLPOS |
language |
eng |
topic |
Computer science. Artificial intelligence. Computer Science. Artificial Intelligence (incl. Robotics). Computer science. Artificial intelligence. Computer Science. Artificial Intelligence (incl. Robotics). |
spellingShingle |
Computer science. Artificial intelligence. Computer Science. Artificial Intelligence (incl. Robotics). Computer science. Artificial intelligence. Computer Science. Artificial Intelligence (incl. Robotics). Utgoff, Paul E. author. SpringerLink (Online service) Machine Learning of Inductive Bias [electronic resource] / |
description |
This book is based on the author's Ph.D. dissertation[56]. The the sis research was conducted while the author was a graduate student in the Department of Computer Science at Rutgers University. The book was pre pared at the University of Massachusetts at Amherst where the author is currently an Assistant Professor in the Department of Computer and Infor mation Science. Programs that learn concepts from examples are guided not only by the examples (and counterexamples) that they observe, but also by bias that determines which concept is to be considered as following best from the ob servations. Selection of a concept represents an inductive leap because the concept then indicates the classification of instances that have not yet been observed by the learning program. Learning programs that make undesir able inductive leaps do so due to undesirable bias. The research problem addressed here is to show how a learning program can learn a desirable inductive bias. |
format |
Texto |
topic_facet |
Computer science. Artificial intelligence. Computer Science. Artificial Intelligence (incl. Robotics). |
author |
Utgoff, Paul E. author. SpringerLink (Online service) |
author_facet |
Utgoff, Paul E. author. SpringerLink (Online service) |
author_sort |
Utgoff, Paul E. author. |
title |
Machine Learning of Inductive Bias [electronic resource] / |
title_short |
Machine Learning of Inductive Bias [electronic resource] / |
title_full |
Machine Learning of Inductive Bias [electronic resource] / |
title_fullStr |
Machine Learning of Inductive Bias [electronic resource] / |
title_full_unstemmed |
Machine Learning of Inductive Bias [electronic resource] / |
title_sort |
machine learning of inductive bias [electronic resource] / |
publisher |
Boston, MA : Springer US, |
publishDate |
1986 |
url |
http://dx.doi.org/10.1007/978-1-4613-2283-2 |
work_keys_str_mv |
AT utgoffpauleauthor machinelearningofinductivebiaselectronicresource AT springerlinkonlineservice machinelearningofinductivebiaselectronicresource |
_version_ |
1756264180703297536 |