Timezone: »

 
Poster
Bounds on the Approximation Power of Feedforward Neural Networks
Mohammad Mehrabi · Aslan Tchamkerten · MANSOOR I YOUSEFI

Wed Jul 11 09:15 AM -- 12:00 PM (PDT) @ Hall B #174

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.

Author Information

Mohammad Mehrabi (Sharif University of Technology)
Aslan Tchamkerten (Telecom ParisTech)
MANSOOR I YOUSEFI (Telecom ParisTech)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors