\dm_csml_event_details UCL ELLIS

Invariance & invertibility in CNNs


Speaker

Edouard Oyallon

Affiliation

CentraleSupelec

Date

Friday, 26 January 2018

Time

13:00-14:00

Location

Zoom

Link

Roberts Building G08 Sir David Davies LT

Event series

DeepMind/ELLIS CSML Seminar Series

Abstract

Outstanding supervised classification performances obtained by CNNs indicate they have the ability to create relevant invariants for classification. We show that this can be achieved through progressive invariance incorporation and as well via perfectly invertible architectures. Illustrations are given through Hybrid Scattering Networks, based on a geometric representation, and $i$-RevNets, a class of invertible CNNs. We explicit several empirical properties, like progressive linear separability, in order to shed light on the inner mechanisms implemented by CNNs.

Biography