Approximate Inference and Scientific Method

Abstract

A new identification criterion, motivated by notions of successively improving approximations in the philosophy of science, is defined. It is shown that the class of recursive functions is identifiable under this criterion. This result is extended to permit somewhat more realistic types of data than usual. This criterion is then modified to consider restrictions on the quality of approximations. (JHD)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1989
Accession Number
ADA221747

Entities

People

  • Mark Fulk
  • Sanjay K Jain

Organizations

  • University of Rochester

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Computations
  • Computer Science
  • Computers
  • Identification
  • Information Science
  • Language
  • Machine Learning
  • Machines
  • New York
  • Notation
  • Recursive Functions
  • Scientific Theories
  • Sequences
  • Theorems
  • Theoretical Computer Science
  • Universities

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms