Algorithm Selection Framework: A Holistic Approach to the Algorithm Selection Problem

Abstract

The algorithm selection framework uses a combination of user input and meta-data to streamline the algorithm selection for any data analysis task. The framework removes the conjecture of the common trial and error strategyand generates a ranked list of recommended analysis techniques. In seven of nine sample problems, the recall of the top ranked recommendation was considered "good" with at least 90% of the best observed recall. Pareto efficientrecommendations for recall and run time were generated for three of the problems. The framework measured well against the pre-defined criteria. The framework successfully used information in the problem to recommend appropriate algorithms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 26, 2020
Accession Number
AD1102878

Entities

People

  • Marc W. Chale

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Artificial Neural Networks
  • Bayesian Networks
  • Big Data
  • Computational Science
  • Computers
  • Data Analysis
  • Data Mining
  • Data Science
  • Department Of Defense
  • Digital Data
  • Information Processing
  • Information Science
  • Kernel Functions
  • Machine Learning
  • Operations Research
  • Supervised Machine Learning
  • United States

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Defense Acquisition Program Management
  • Neural Network Machine Learning.