Incorporating Reinforcement Learning for Quality-aware Sample Selection in Deep Architecture Training.
Gereziher AdhaneMohammad Mahdi DehshibiDavid MasipPublished in: COINS (2022)
Keyphrases
- sample selection
- quality aware
- reinforcement learning
- active learning
- training data
- training examples
- support vector machine
- supervised learning
- function approximation
- learning algorithm
- learning capabilities
- selection strategy
- markov decision processes
- neural network
- transfer learning
- optimal policy
- cost sensitive
- training samples
- semi supervised learning
- learning process
- image processing
- deep architectures
- data sets