Measuring Classifier Intelligence

Abstract

Classifiers are seen here as systems in which input feature values are used with fitted or learned functions that produce output values which are interpreted as probabilities or fuzzy degrees of class membership, or in which output values are used with cut-off decision rules to choose bivalent class membership. Two complementary measurements for evaluating training, validation, testing, and deployment phase performances in human, mechanical, and computerized classifiers are proposed here. These measurements are derived from samples of classifier output values paired with their corresponding known probabilistic, fuzzy, or bivalent classification values. The first measurement is the area under the ROC plot. The second is the separation index newly introduced here. Both of these measurements are easy to understand and to compute. It is proposed that they be considered standard metrics for evaluating and comparing classifier intelligence.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2002
Accession Number
ADA511068

Entities

People

  • Jim Deleo

Organizations

  • National Institutes of Health

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Abstracts
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Classification
  • Computational Science
  • Data Mining
  • Databases
  • Deployment
  • Information Science
  • Intelligent Agents
  • Intelligent Systems
  • Machine Learning
  • Mathematical Models
  • Neural Networks
  • Probability
  • Training
  • Validation

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Oncology and Biomarker-Based Cancer Detection.
  • Psychometric Testing or Psychological Assessment.