On the near optimality of the stochastic approximation of smooth functions by neural networks.
Vitaly MaiorovRon MeirPublished in: Adv. Comput. Math. (2000)
Keyphrases
- stochastic approximation
- smooth functions
- neural network
- monte carlo
- closely related
- basis functions
- receptive fields
- input space
- artificial neural networks
- reinforcement learning
- back propagation
- policy iteration
- multilayer perceptron
- image segmentation
- mumford shah functional
- feed forward
- optimal solution
- recurrent neural networks
- gaussian process
- theoretical guarantees
- optimal policy
- training data
- semi supervised