PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
July 1, 1982IEEE Transactions on Pattern Analysis and Machine Intelligence183 citations

Hierarchical Classifier Design Using Mutual Information

View Full Paper
ISIshwar K. SethiGSG. P. R. Sarvarayudu

Key Points

  • To develop a nonparametric algorithm for hierarchical partitioning of feature space using mutual information.
  • Developed a nonparametric algorithm based on average mutual information for hierarchical partitioning.
  • Generated an efficient partitioning tree to minimize the probability of error.
  • Demonstrated the algorithm with examples including handprinted numeral recognition.
  • The algorithm effectively maximized average mutual information gain at each partitioning step.
  • Generated a confidence bound expression for the classifier's performance.
  • Showed practical effectiveness in multifeature multicategory pattern recognition problems, including numeral recognition.

Abstract

A nonparametric algorithm is presented for the hierarchical partitioning of the feature space. The algorithm is based on the concept of average mutual information, and is suitable for multifeature multicategory pattern recognition problems. The algorithm generates an efficient partitioning tree for specified probability of error by maximizing the amount of average mutual information gain at each partitioning step. A confidence bound expression is presented for the resulting classifier. Three examples, including one of handprinted numeral recognition, are presented to demonstrate the effectiveness of the algorithm.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Sethi et al. (1982) studied this question.

synapsesocial.com/papers/6a07edc47ad161a3abfe0a51https://doi.org/10.1109/tpami.1982.4767278
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A combined nonparametric approach to feature selection and binary decision tree design1980 · 101 citations
  2. 2THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS1936 · 14,888 citations
  3. 3Problem-Solving Models and Search Strategies for Pattern Recognition1979 · 76 citations
  4. 4Transmission of Information.1962 · 364 citations
  5. 5An Algorithm for Constructing Optimal Binary Decision Trees1977 · 91 citations