Mechanical Turkeys: Mechanical Turkeys: G. Belot.
Some learning strategies that work well when computational considerations are abstracted away from become severely limiting when such considerations are taken into account. We illustrate this phenomenon for agents who attempt to extrapolate patterns in binary data streams chosen from among a countab...
| Published in: | Journal of Philosophical Logic Vol. 54; no. 1; pp. 197 - 219 |
|---|---|
| Main Author: | |
| Format: | Article |
| Published: |
Springer Nature
Feb2025
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=183283956&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 183283956 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00223611 JPH jtl: Journal of Philosophical Logic issn: 00223611 maglogo: N pubinfo: dt: Feb2025 vid: 54 iid: 1 pid: 237 pub: Springer Nature artinfo: ui: 183283956 10.1007/s10992-025-09784-9 ppf: 197 ppct: 22 formats: fmt: @attributes: type: P size: 352KB tig: atl: Mechanical Turkeys: Mechanical Turkeys: G. Belot. aug: au: Belot, Gordon affil: https://ror.org/00jmfr291 Department of Philosophy, University of Michigan, 435 South State Street, 48104, Ann Arbor, MI, USA su: Big data Simplicity sug: subj: Big data Simplicity keyword: Bayesian learning Computable Bayesianism Induction Learning by enumeration ab: Some learning strategies that work well when computational considerations are abstracted away from become severely limiting when such considerations are taken into account. We illustrate this phenomenon for agents who attempt to extrapolate patterns in binary data streams chosen from among a countable family of possibilities. If computational constraints are ignored, then two strategies that will always work are learning by enumeration (enumerate the possibilities—in order of simplicity, say—then search for the one earliest in the ordering that agrees with your data and use it to predict the next data point) and Bayesian learning. But there are many families of computable data streams that, although they can be successfully extrapolated by computable agents, cannot be handled by any computable learner by enumeration. And while there is a sense in which Bayesian learning is a fully general strategy for computable learners, the ability to mimic powerful learners comes at a price for Bayesians: they cannot, in general, become highly confident of their predictions in the limit of large data sets and they cannot, in general, use priors that incorporate all relevant background knowledge. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Journal of Philosophical Logic is a copyright of Springer, 2025. All Rights Reserved. item: Journal of Philosophical Logic holder: Springer Nature dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|