ICONIP
2008
13 years 5 months ago
2008
Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been...
ETVC
2008
13 years 6 months ago
2008
In a seminal paper, Amari (1998) proved that learning can be made more efficient when one uses the intrinsic Riemannian structure of the algorithms' spaces of parameters to po...