Learning algorithm by reinforcement signals for the automatic recognition system.
Koichi IkutaHiroaki TanakaKen-ichi TanakaKazuo KyumaPublished in: SMC (5) (2004)
Keyphrases
- upper bound
- learning algorithm
- sample complexity
- reinforcement learning
- training data
- signal processing
- feature extraction
- active learning
- machine learning algorithms
- fully automatic
- data driven
- learning scheme
- learning problems
- spectral analysis
- data sets
- recognition process
- learning tasks
- semi automatic
- unlabeled data
- supervised learning