September 16 2019
Subject:AI&Robotics lunch seminar, Prof. Dr. Max WellingHost Prof.dr. Dariu Gavrila
We are pleased to invite you to attend the lunch seminar:
Monday October 7
3mE-Collegezaal C
Building number: 34
Lunch buffet open from 12.30
- For lunch reservation accept the outlook invitation or send your e-mail to k.j.vantongeren@tudelft.nl (before October 2)
- Please forward this invitation to interested students and employees
Title:From Physics to Deep Learning: Gauge and Quantum Inspired
Convolutions
Abstract:
One of the workhorses of deep learning is convolutions. Convolutions encode translation
invariance (or equivariance) in the representations of the NN. Convolutions have been extended to graph convolutions and group convolutions in NNs; a field known as "geometric deep learning".
In this talk I will present two new types of convolutions inspired by some of the most fundamental theories of physics, gauge convolutions (on a mesh) and quantum convolutions.
Gauge convolutions represent the mathematically sound way to perform deep learning on a curved manifold, and are deeply related to general relativity.
Quantum inspired convolutions (QUICKs) introduce new representations and more powerful convolutions based on the notion of entanglement of qubits. While QUICK can be executed on future quantum computers we introduce it here as a practical tool for classical deep learning.
in collaboration with:
Maurice Weiler, Pim de Haan and Taco Cohen (gauge convolutions)
Roberto Bondesan (quantum convolutions)
Bio:
Prof. Dr. Max Welling is a research chair in Machine Learning at the University of Amsterdam and a VP Technologies at Qualcomm. He has a secondary appointment as a senior fellow at the Canadian Institute for Advanced Research (CIFAR).
He is co-founder of “Scyfer BV” a university spin-off in deep learning which got acquired by Qualcomm in summer 2017.
In the past he held postdoctoral positions at Caltech (’98-’00), UCL (’00-’01) and the U. Toronto (’01-’03). He received his PhD in ’98 under supervision of Nobel laureate Prof. G. ‘t Hooft.
Max Welling has served as associate editor in chief of IEEE TPAMI from 2011-2015 (impact factor 4.8). He serves on the executive board of the NeurIPS foundation since 2015 (the largest conference in machine learning) and has been program chair and general chair of NeurIPS in 2013 and 2014 respectively. He was also program chair of AISTATS in 2009 and ECCV in 2016 and general chair of MIDL 2018.
Welling currently serves on the board of the ELLIS foundation and has served on the editorial boards of JMLR and JMLR. He is recipient of the ECCV Koenderink Prize in 2010. Welling directs the Amsterdam Machine Learning Lab (AMLAB), and co-directs the Qualcomm-UvA deep learning lab (QUVA) and the Bosch-UvA Deep Learning lab (DELTA).
We are looking forward to see you all on October 7th
Kind regards,
Karin van Tongeren
Secretary Robotics Institute
