Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification.
Pawel PiwekAdam KlukowskiTianyang HuPublished in: CoRR (2023)
Keyphrases
- support vector
- classification algorithm
- classification systems
- decision trees
- classification models
- classification method
- feature selection
- class labels
- machine learning methods
- classification rate
- rule based classifier
- svm classifier
- supervised classification
- training set
- classification accuracy
- multi category
- complexity measures
- classifier combination
- confusion matrix
- improves the classification accuracy
- classification process
- optimum path forest
- multiple classifiers
- k nearest neighbour
- nearest neighbour
- classifier ensemble
- diversity measures
- classification procedure
- feature vectors
- classification schemes
- accurate classification
- multiclass classification
- machine learning algorithms
- naive bayes
- training samples
- classification scheme
- machine learning
- discriminant functions
- support vector machine svm
- correctly classified
- support vector machine classifiers
- text classification
- multiple classifier systems
- image classification
- majority voting
- training data
- nearest neighbor classifier
- extracted features
- support vector machine
- feature extraction
- bayesian classifier
- imbalanced data sets
- feature set
- decision boundary
- sufficient training data
- pattern recognition
- classification decisions
- probabilistic classifiers
- similarity measure
- decision tree classifiers
- accurate classifiers
- fold cross validation
- ensemble classifier
- binary classifiers
- multi class
- distance measure
- training examples