A derivation of minimum classification error from the theoretical classification risk using Parzen estimation.
Erik McDermottShigeru KatagiriPublished in: Comput. Speech Lang. (2004)
Keyphrases
- density estimation
- discriminative training
- minimum classification error
- pattern recognition
- classification accuracy
- machine learning
- probabilistic interpretation
- feature space
- decision trees
- cost sensitive
- knn
- support vector machine
- least squares
- supervised learning
- model selection
- mixture model
- training samples
- cross validation
- machine learning methods
- high dimensional
- training set
- support vector
- statistical pattern recognition
- bayesian networks
- feature extraction