Bounds on the Approximation Power of Feedforward Neural Networks
By M. Mehrabi, A. Tchamkerten, Mansoor I. Yousefi. 2018
12 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Mechanical Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Lalitha Sankar
- Jiachun Liao
- Peter Kairouz
- Mario Díaz
- Pramod Viswanath
- Sewoong Oh
- Min Ye
- Alexander Barg
Citations in the corpus
- Theoretical Guarantees for Model Auditing with Finite Adversaries (2019, background): “The latter results characterize how well certain functions can be approximated using neural networks, see [16, 17, 20–25] and references therein.”