ADV-ResNet: Residual Network with Controlled Adversarial Regularization for Effective Classification of Practical Time Series Under Training Data Scarcity Problem.
Arijit UkilLeandro MarínAntonio JaraPublished in: IJCNN (2022)
Keyphrases
- training data
- classification accuracy
- decision trees
- classification models
- training set
- supervised learning
- class labels
- pattern recognition
- training samples
- support vector machine
- training dataset
- peer to peer
- classification method
- text classification
- support vector machine svm
- test data
- machine learning algorithms
- sufficient training data
- training process
- feature values
- accurate classifiers
- data sets
- feature space
- real world
- machine learning
- prior knowledge
- multi class
- cross validation
- wireless sensor networks
- feature vectors
- network structure
- cost sensitive
- image classification
- dynamic time warping
- support vector
- feature extraction
- learning algorithm
- radial basis function network
- unseen data
- multi variate
- training examples