Function approximation by deep neural networks with parameters {0,±1/2, ± 1, 2}
In this paper it is shown that C_β-smooth functions can be approximated by neural networks with parameters {0,±1/2, ± 1, 2}. The depth, width and the number of active parameters of constructed networks have, up to a logarithimc factor, the same dependence on the approximation error as the networks with parameters in [-1,1]. In particular, this means that the nonparametric regression estimation with constructed networks attain the same convergence rate as with the sparse networks with parameters in [-1,1].
READ FULL TEXT