Improving Covariance Matrices Derived from Tiny Training Datasets for the Classification of Event-Related Potentials with Linear Discriminant Analysis.
Jan SosulskiJan-Philipp KemmerMichael TangermannPublished in: Neuroinformatics (2021)
Keyphrases
- linear discriminant analysis
- training dataset
- covariance matrices
- small sample size
- support vector machine svm
- feature extraction
- covariance matrix
- support vector
- feature space
- discriminant analysis
- principal component analysis
- fisher criterion
- face recognition
- discriminant information
- feature vectors
- pattern recognition
- classification accuracy
- dimensionality reduction
- eeg signals
- null space
- training samples
- class labels
- support vector machine
- training set
- high dimensional
- sample size
- image classification
- high dimensional data
- neural network
- training data
- maximum likelihood
- distance measure
- feature selection
- gaussian distribution
- computer vision
- vector space
- text classification
- gaussian mixture
- signal processing
- supervised learning
- active learning
- decision trees