Bounds on the Approximation Power of Feedforward Neural Networks

06/29/2018
by   Mohammad Mehrabi, et al.
0

The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are established in terms of the approximation error and network depth and width. These bounds improve upon state-of-the-art bounds for certain classes of functions, such as strongly convex functions. Second, an upper bound is established on the difference of two neural networks with identical weights but different activation functions.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset