Julien Mairal

Wednesday - 24 October 2018

Time: 4.00pm

Ground Floor Seminar Room

25 Howland Street, London, W1T 4JG

Invariance and Stability of Deep Convultional Represantations

In this work, we study invariant properties of convolutional neural networks, their stability to image deformations, and their model complexity from a kernel point of view. This is achieved by generalizing the multilayer kernel construction introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable and that models from this functional space, such as a large class of convolutional neural networks with homogeneous activation functions, may enjoy the same stability. In particular, we study the norm of such models, which acts as a measure of complexity that controls both stability and generalization. This is a joint work with Alberto Bietti.