Universal approximation bounds for superpositions of a sigmoidal function.
Andrew R. BarronPublished in: IEEE Trans. Inf. Theory (1993)
Keyphrases
- linear functions
- error bounds
- vc dimension
- series expansion
- approximation methods
- approximation error
- upper bound
- stage stochastic programs
- continuous functions
- error tolerance
- pointwise
- expected error
- approximation algorithms
- average case
- reinforcement learning
- lower and upper bounds
- turing machine
- linear approximation
- multi valued
- sufficient statistics
- relative error
- piecewise constant
- activation function
- boolean functions
- worst case
- lower bound
- support vector