Timezone: »
Oral
Bounds on the Approximation Power of Feedforward Neural Networks
Mohammad Mehrabi · Aslan Tchamkerten · MANSOOR I YOUSEFI
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)
-
2018 Poster: Bounds on the Approximation Power of Feedforward Neural Networks »
Wed. Jul 11th 04:15 -- 07:00 PM Room Hall B #174___0
More from the Same Authors
-
2021 Poster: Fundamental Tradeoffs in Distributionally Adversarial Training »
Mohammad Mehrabi · Adel Javanmard · Ryan A. Rossi · Anup Rao · Tung Mai -
2021 Spotlight: Fundamental Tradeoffs in Distributionally Adversarial Training »
Mohammad Mehrabi · Adel Javanmard · Ryan A. Rossi · Anup Rao · Tung Mai