Locally Linear Attributes of ReLU Neural Networks
arXiv:2012.01940
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.
18 pages, 12 figures, 2 tables, submitted to SIMODS