A Differential Theory of Learning for Efficient Statistical Pattern Recognition

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 classifie...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Hampshire, John, Kumar, B V
Format:	Report
Sprache:	eng
Schlagworte:	BAYES THEOREM CFM(CLASSIFICATION FIGURE OF MERIT) CLASSIFICATION CLASSIFIERS Cybernetics DIFFERENTIAL LEARNING DISCRIMINATE ANALYSIS EXPERIMENTAL DESIGN INPUT OUTPUT MODELS LEARNING LEARNING MACHINES NEURAL NETS OPTICAL CHARACTER RECOGNITION PATTERN RECOGNITION PE61102F PROBABILITY STATISTICAL ANALYSIS Statistics and Probability STRATEGY THEORY TRAINING WUAFOSR2305B3
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	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.