On ε-Optimality of the Pursuit Learning Algorithm.
Ryan MartinOmkar J. TilakPublished in: J. Appl. Probab. (2012)
Keyphrases
- learning algorithm
- active learning
- training data
- optimal solution
- supervised learning
- machine learning algorithms
- machine learning
- learning scheme
- learning rate
- learning tasks
- training samples
- generalization ability
- learning problems
- back propagation
- case study
- machine learning methods
- data sets
- labeled data
- generalization error
- reinforcement learning
- reinforcement learning algorithms