A Differential Theory of Learning for Efficient Statistical Pattern Recognition
Abstract
Probabilistic learning strategies currently use are inefficient, requiring high classifier complexity and large training samples. In this report, we introduce and analyze an asymptotically efficient differential learning strategy. It guarantees the best generalization allowed by the chosen classifier paradigm. Differential learning also requires the classifier with minimal complexity. The theory is demonstrated in several real-world machine learning/pattern recognition tasks. Learning, Pattern recognition, Classification, Neural networks.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 15, 1993
- Accession Number
- ADA277313
Entities
People
- B. V. Kumar
- John Hampshire
Organizations
- Carnegie Mellon University