PhilSci Archive

Universal Prediction

Sterkenburg, Tom F. (2018) Universal Prediction.

This is the latest version of this item.

[img]
Preview
Text
proeffin.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial.

Download (1MB) | Preview

Abstract

In this dissertation I investigate the theoretical possibility of a universal method of prediction. A prediction method is universal if it is always able to learn what there is to learn from data: if it is always able to extrapolate given data about past observations to maximally successful predictions about future observations. The context of this investigation is the broader philosophical question into the possibility of a formal specification of inductive or scientific reasoning, a question that also touches on modern-day speculation about a fully automatized data-driven science.

I investigate, in particular, a specific mathematical definition of a universal prediction method, that goes back to the early days of artificial intelligence and that has a direct line to modern developments in machine learning. This definition essentially aims to combine all possible prediction algorithms. An alternative interpretation is that this definition formalizes the idea that learning from data is equivalent to compressing data. In this guise, the definition is often presented as an implementation and even as a justification of Occam's razor, the principle that we should look for simple explanations.

The conclusions of my investigation are negative. I show that the proposed definition cannot be interpreted as a universal prediction method, as turns out to be exposed by a mathematical argument that it was actually intended to overcome. Moreover, I show that the suggested justification of Occam's razor does not work, and I argue that the relevant notion of simplicity as compressibility is problematic itself.


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

Item Type: Published Article or Volume
Creators:
CreatorsEmailORCID
Sterkenburg, Tom F.tom.sterkenburg@lmu.de0000-0002-4860-727X
Additional Information: PhD dissertation, University of Groningen
Subjects: Specific Sciences > Computation/Information > Classical
Specific Sciences > Artificial Intelligence
General Issues > Confirmation/Induction
Specific Sciences > Probability/Statistics
Depositing User: Mr Tom Sterkenburg
Date Deposited: 17 Sep 2018 16:04
Last Modified: 17 Sep 2018 16:04
Item ID: 14486
Publisher: University of Groningen
Official URL: https://ir.cwi.nl/pub/27326
DOI or Unique Handle: 11370/075527b0-ef4e-473b-ba36-60a78f8de362
Subjects: Specific Sciences > Computation/Information > Classical
Specific Sciences > Artificial Intelligence
General Issues > Confirmation/Induction
Specific Sciences > Probability/Statistics
Date: January 2018
URI: https://philsci-archive.pitt.edu/id/eprint/14486

Available Versions of this Item

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Altmetric.com

Actions (login required)

View Item View Item