Adaptive associative reward-penalty algorithms for sigma-pi networks.
Richard Stuart NevilleT. John StonhamPublished in: Neural Parallel Sci. Comput. (1994)
Keyphrases
- computational cost
- computational efficiency
- computer networks
- learning algorithm
- significant improvement
- machine learning
- recently developed
- theoretical analysis
- reinforcement learning
- social networks
- data streams
- data structure
- benchmark datasets
- image segmentation
- complex networks
- real time
- inverse reinforcement learning