Extension of localised approximation by neural networks
Nahmwoo Hahm, Bum Il Hong · Bulletin of the Australian Mathematical Society · 1999
We prove generalised results for localised approximation by generalised translation networks. We also show the relationship between the minimum number of neurons in the generalised translation networks with one hidden layer and the desired accuracy where the target functions are in a subset V1, p ([−1, 1]s) of the Sobolev space W1, p([−1, 1]s).