Is Unsupervised Clustering Somehow Truer? Is Unsupervised Clustering Somehow Truer?

Scientists increasingly approach the world through machine learning techniques, but philosophers of science often question their epistemic status. Some philosophers have argued that the use of unsupervised clustering algorithms is more justified than the use of supervised classification, because sup...

Full description

Saved in:
Bibliographic Details
Published in:Minds and machines (Dordrecht) Vol. 34; no. 4
Main Author: Søgaard, Anders
Format: Journal Article
Language:English
Published: Dordrecht Springer Netherlands 29.10.2024
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Classification
Clustering
Cognitive Psychology
Computer Science
Economics
Game Theory
Machine learning
Philosophy of Mind
Philosophy of Science
Social and Behav. Sciences
Theory of Computation
Epistemic status
Supervised classification
Unsupervised clustering
Overfitting
ISSN:1572-8641, 0924-6495, 1572-8641
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Scientists increasingly approach the world through machine learning techniques, but philosophers of science often question their epistemic status. Some philosophers have argued that the use of unsupervised clustering algorithms is more justified than the use of supervised classification, because supervised classification is more biased, and because (parametric) simplicity plays a different and more interesting role in unsupervised clustering. I call these arguments the No-Bias Argument and the Simplicity-Truth Argument . I show how both arguments are fallacious and how, on the contrary, the use of supervised classification is at least as justified as the use of unsupervised clustering.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1572-8641
0924-6495
1572-8641
DOI:10.1007/s11023-024-09699-5