PhilSci Archive

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

Sterkenburg, Tom F. (2017) Putnam's Diagonal Argument and the Impossibility of a Universal Learning Machine. [Preprint]

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

Download (413kB) | Preview


Putnam (1963) construed the aim of Carnap's program of inductive logic as the specification of an "optimum" or "universal" learning machine, and presented a diagonal proof against the very possibility of such a thing. Yet the ideas of Solomonoff (1964) and Levin (1970) lead to a mathematical foundation of precisely those aspects of Carnap's program that Putnam took issue with, and in particular, resurrect the notion of a universal learning machine.

This paper takes up the question whether the Solomonoff-Levin proposal is successful in this respect. I expose the general strategy to evade Putnam's argument, leading to a broader discussion of the outer limits of mechanized Bayesian induction. I argue that this strategy ultimately still succumbs to diagonalization, reinforcing Putnam's impossibility claim.

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

Item Type: Preprint
Sterkenburg, Tom
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: 06 Jan 2017 14:52
Last Modified: 06 Jan 2017 14:52
Item ID: 12733
Subjects: General Issues > Confirmation/Induction
Date: 2017

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