Max-Min Representation of Piecewise Linear Functions

By Sergei Ovchinnikov. 2000

118 citations recorded by the source corpus.

It is shown that a piecewise linear function on a convex domain in R d can be represented as a boolean polynomial in terms of its linear components.

Subfields: Computer Graphics and Computer-Aided Design, Signal Processing

View Paper: https://www.semanticscholar.org/paper/ef3d50c3736b278b3c0d8e1ffb2ff6cdd31eea6b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Signal Processing

1. Raman Arora

Citations in the corpus

• Understanding Deep Neural Networks with Rectified Linear Units (2016, background): “The universal approximation result was first given by Cybenko in 1989 for sigmoidal activation function (Cybenko, 1989), and later generalized by Hornik to an arbitrary bounded and nonconstant activation function Hornik (1991).”
• Model predictive control for perturbed continuous piecewise affine systems with bounded disturbances (2004, unknown): “Using the results of [4], [8] we can prove thatcontinuousPWA systems are equivalent with MMPS systems.”