Fact-Free Learning

Enriqueta Aragones; Itzhak Gilboa; Andrew Postlewaite; David Schmeidler

doi:https://doi.org/10.1142/9789814366182_0008

Fact-Free Learning

Enriqueta Aragones, Itzhak Gilboa, Andrew Postlewaite, David Schmeidler

Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

People may be surprised by noticing certain regularities that hold in existing knowledge they have had for some time. That is, they may learn without getting new factual information. We argue that this can be partly explained by computational complexity. We show that, given a knowledge base, finding a small set of variables that obtain a certain value of R2 is computationally hard, in the sense that this term is used in computer science.We discuss some of the implications of this result and of fact-free learning in general.

Original language	English
Title of host publication	Case-Based Predictions
Subtitle of host publication	An Axiomatic Approach to Prediction, Classification and Statistical Learning
Pages	185-210
Number of pages	26
ISBN (Electronic)	9789814366182
DOIs	https://doi.org/10.1142/9789814366182_0008
State	Published - 1 Jan 2012

Keywords

Bounded rationality
Complexity
Learning
Regression

All Science Journal Classification (ASJC) codes

General Economics,Econometrics and Finance
General Business,Management and Accounting
General Mathematics

Access to Document

https://doi.org/10.1142/9789814366182_0008

Cite this

@inbook{f64d86822e1d4f7d957ea69854a49f4b,

title = "Fact-Free Learning",

abstract = "People may be surprised by noticing certain regularities that hold in existing knowledge they have had for some time. That is, they may learn without getting new factual information. We argue that this can be partly explained by computational complexity. We show that, given a knowledge base, finding a small set of variables that obtain a certain value of R2 is computationally hard, in the sense that this term is used in computer science.We discuss some of the implications of this result and of fact-free learning in general.",

keywords = "Bounded rationality, Complexity, Learning, Regression",

author = "Enriqueta Aragones and Itzhak Gilboa and Andrew Postlewaite and David Schmeidler",

year = "2012",

month = jan,

day = "1",

doi = "https://doi.org/10.1142/9789814366182_0008",

language = "الإنجليزيّة",

isbn = "981436617X",

pages = "185--210",

booktitle = "Case-Based Predictions",

}

TY - CHAP

T1 - Fact-Free Learning

AU - Aragones, Enriqueta

AU - Gilboa, Itzhak

AU - Postlewaite, Andrew

AU - Schmeidler, David

PY - 2012/1/1

Y1 - 2012/1/1

N2 - People may be surprised by noticing certain regularities that hold in existing knowledge they have had for some time. That is, they may learn without getting new factual information. We argue that this can be partly explained by computational complexity. We show that, given a knowledge base, finding a small set of variables that obtain a certain value of R2 is computationally hard, in the sense that this term is used in computer science.We discuss some of the implications of this result and of fact-free learning in general.

AB - People may be surprised by noticing certain regularities that hold in existing knowledge they have had for some time. That is, they may learn without getting new factual information. We argue that this can be partly explained by computational complexity. We show that, given a knowledge base, finding a small set of variables that obtain a certain value of R2 is computationally hard, in the sense that this term is used in computer science.We discuss some of the implications of this result and of fact-free learning in general.

KW - Bounded rationality

KW - Complexity

KW - Learning

KW - Regression

UR - http://www.scopus.com/inward/record.url?scp=85180042336&partnerID=8YFLogxK

U2 - https://doi.org/10.1142/9789814366182_0008

DO - https://doi.org/10.1142/9789814366182_0008

M3 - فصل

SN - 981436617X

SN - 9789814366175

SP - 185

EP - 210

BT - Case-Based Predictions

ER -

Fact-Free Learning

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this