Greedy information acquisition algorithm: a new information theoretic approach to dynamic information acquisition in neural networks.
Ryotaro KamimuraTaeko KamimuraHaruhiko TakeuchiPublished in: Connect. Sci. (2002)
Keyphrases
- information acquisition
- neural network
- experimental evaluation
- search space
- computational cost
- optimization algorithm
- cost function
- dynamic programming
- learning algorithm
- worst case
- significant improvement
- pattern recognition
- decision making
- fuzzy logic
- k means
- expectation maximization
- segmentation algorithm
- multistage
- matching algorithm
- convergence rate
- training process
- training algorithm
- hill climbing
- greedy strategy