Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theorem

06/27/2019
by   Hadrien Montanelli, et al.
0

We prove a theorem concerning the approximation of multivariate continuous functions by deep ReLU networks, for which the curse of the dimensionality is lessened. Our theorem is based on the Kolmogorov--Arnold superposition theorem, and on the approximation of the inner and outer functions that appear in the superposition by very deep ReLU networks.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset