On Lipschitz Bounds of General Convolutional Neural Networks [article]

Dongmian Zou, Radu Balan, Maneesh Singh
2018 arXiv   pre-print
Many convolutional neural networks (CNNs) have a feed-forward structure. In this paper, a linear program that estimates the Lipschitz bound of such CNNs is proposed. Several CNNs, including the scattering networks, the AlexNet and the GoogleNet, are studied numerically and compared to the theoretical bounds. Next, concentration inequalities of the output distribution to a stationary random input signal expressed in terms of the Lipschitz bound are established. The Lipschitz bound is further
more » ... to establish a nonlinear discriminant analysis designed to measure the separation between features of different classes.
arXiv:1808.01415v1 fatcat:f5fkbyaiobhe3jfgcfuw4sunom