2000 character limit reached
Locally Linear Attributes of ReLU Neural Networks (2012.01940v1)
Published 30 Nov 2020 in cs.LG and cs.CV
Abstract: A ReLU neural network determines/is a continuous piecewise linear map from an input space to an output space. The weights in the neural network determine a decomposition of the input space into convex polytopes and on each of these polytopes the network can be described by a single affine mapping. The structure of the decomposition, together with the affine map attached to each polytope, can be analyzed to investigate the behavior of the associated neural network.