How Gruesome are the No-free-lunch Theorems for Machine Learning? Cover Image
  • Price 5.00 €

How Gruesome are the No-free-lunch Theorems for Machine Learning?
How Gruesome are the No-free-lunch Theorems for Machine Learning?

Author(s): Davor Lauc
Subject(s): Epistemology, Logic, Analytic Philosophy
Published by: KruZak
Keywords: Induction; the problem of; No-free-lunch theorems; The new riddle of induction;

Summary/Abstract: No-free-lunch theorems are important theoretical result in the fields of machine learning and artificial intelligence. Researchers in this fields often claim that the theorems are based on Hume’s argument about induction and represent a formalisation of the argument. This paper argues that this is erroneous but that the theorems correspond to and formalise Goodman’s new riddle of induction. To demonstrate the correspondence among the theorems and Goodman’s argument, a formalisation of the latter in the spirit of the former is sketched.

  • Issue Year: XVIII/2018
  • Issue No: 54
  • Page Range: 479-485
  • Page Count: 7
  • Language: English