Supplementing training with data from a shifted distribution for machine learning classifiers: adding more cases may not always help.
Kenny H. ChaAlexej GossmannNicholas PetrickBerkman SahinerPublished in: Medical Imaging: Image Perception, Observer Performance, and Technology Assessment (2020)
Keyphrases
- machine learning
- data analysis
- data processing
- data sets
- training data
- training samples
- database
- training examples
- probability distribution
- test data
- data collection
- image data
- data distribution
- data structure
- knowledge discovery
- training and testing data
- training and test data
- data mining techniques
- supervised classification
- statistical analysis
- original data
- decision trees
- feature selection
- neural network
- data sources
- labeled training data
- data quality
- machine learning methods
- learning algorithm
- machine learning algorithms
- naive bayes
- support vector
- labeled data
- artificial neural networks
- feature vectors
- input data
- natural language processing
- supervised learning