Deep Q-learning for Active Recognition of GERMS: Baseline performance on a standardized dataset for active learning.
Mohsen MalmirKaran SikkaDeborah ForsterJavier R. MovellanGarison CottrellPublished in: BMVC (2015)
Keyphrases
- active learning
- learning algorithm
- reinforcement learning
- recognition rate
- recognition accuracy
- cooperative
- object recognition
- recognition process
- automatic recognition
- function approximation
- selective sampling
- visual recognition
- state space
- feature extraction
- character recognition
- pattern recognition
- database
- multi agent
- optimal policy
- learning strategies
- recognition algorithm
- machine learning
- batch mode
- model free
- training examples
- training dataset
- random sampling
- benchmark datasets
- relevance feedback
- semi supervised
- dynamic programming
- data sets