On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces.
Satoshi HayakawaTaiji SuzukiPublished in: CoRR (2019)
Keyphrases
- neural network
- learning algorithm
- learning systems
- parameter space
- genetic algorithm
- learning process
- neural nets
- learning problems
- high dimensional
- artificial neural networks
- prior knowledge
- reinforcement learning
- unsupervised learning
- back propagation
- active learning
- learning tasks
- pattern recognition
- search algorithm
- inductive inference