Activation Functions Defined on Higher-Dimensional Spaces for Approximation on Compact Sets with and without Scaling.
Yoshifusa ItoPublished in: Neural Comput. (2003)
Keyphrases
- higher dimensional
- activation function
- convex sets
- continuous functions
- euclidean space
- neural network
- feed forward
- approximation spaces
- low dimensional
- hidden layer
- back propagation
- distance transform
- high dimensional
- wavelet packet
- learning algorithm
- learning rate
- neural nets
- network architecture
- basis functions
- multiresolution
- pattern recognition