PhilSci Archive

Putnam's Diagonal Argument and the Impossibility of a Universal Learning Machine

Sterkenburg, Tom F. (2016) Putnam's Diagonal Argument and the Impossibility of a Universal Learning Machine. [Preprint]

WarningThere is a more recent version of this item available.
[img] PDF
solput.pdf - Draft Version

Download (419kB)

Abstract

The diagonalization argument of Putnam (1963) denies the possibility of a universal learning machine. Yet the proposal of Solomonoff (1964) and Levin (1970) promises precisely such a thing. In this paper I discuss how their proposed measure function manages to evade Putnam's diagonalization in one respect, only to fatally fall prey to it in another.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Sterkenburg, Tom F.t.f.sterkenburg@rug.nl
Keywords: diagonal argument, computability, inductive logic, Bayesian confirmation, universal prediction, algorithmic information theory, problem of induction
Subjects: General Issues > Confirmation/Induction
Depositing User: Mr Tom Sterkenburg
Date Deposited: 16 May 2016 15:52
Last Modified: 16 May 2016 15:52
Item ID: 12096
Subjects: General Issues > Confirmation/Induction
Date: 2016
URI: https://philsci-archive.pitt.edu/id/eprint/12096

Available Versions of this Item

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item