APPLIED MATH SEMINAR
Speaker: Stephane Mallat
Applied Mathematics, Ecole Polytechnique, Paris
Title: Classification by Invariant Scattering
When/where: Tuesday, September 14th, 4:15 PM, AKW 200
Abstract:
Signal classes are usually invariant to groups of operators such as
translations or scalings, and to larger Lie groups of deformations.
Classification thus requires finding informative invariants.
Invariants are also at the core of quantum
physics through Gauge theories. We introduce non-linear
invariant operators, similar to quantum scattering. These operators
have small commutators with elastic deformations and
provide new representations of stationary processes.
Their computational architecture reminds deep neural networks, but learning
is needed at a single layer, and implemented with O(N) operations.
State of the art results are shown for image classification
of deformed patterns and random textures.