AN ALGORITHM FOR NONPARAMETRIC PATTERN RECOGNITION.
Abstract
An algorithm is presented for determining decision boundaries based on learning samples in a two-category pattern recognition problem. It is shown that the algorithm yields results which converge in probability to the optimal results (in the sense of minimum probability of error). A confidence bound for the probability of error is obtained. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 17, 1967
- Accession Number
- AD0663109
Entities
People
- Ernest G. Henrichon Jr.