PIMS CRG Summer School: Deep Learning for Computational Mathematics

  • Start Date: 07/22/2019
  • End Date: 07/25/2019
Location: 

Simon Fraser University

Description: 

The purpose of this summer school is to introduce students in applied and computational mathematics to neural networks and deep learning. It will feature three days of lectures and hands-on tutorials, and be followed by a one-day workshop showcasing current research directions and applications, in particular those relating to computational science and engineering. Lectures will cover the foundational mathematics of deep learning, and the tutorials will expose students to their practical implementation in standard software (TensorFlow) on a variety of tasks, including image classi fication, function approximation, and restoration/superresolution.

 

This workshop is aimed at students in applied mathematics or related areas. It assumes no prior knowledge of neural networks. Experience in calculus, linear algebra and analysis and numerical analysis are essential.

 

Program Structure:

 

Monday July 22

10:00 am - 11:00 am: Lecture - "Introduction to Neural Networks”

11:00 am - 11:30 am: Coffee break

11:30 am - 12:30 pm: Lecture - “Introduction to Neural Networks, continued”

12:30 pm - 01:30 pm: Lunch break

01:30 pm - 03:00 pm: Tutorial - “Introduction to Neural Networks with tensorflow”

03:00 pm - 03:30 pm: Coffee break

03:30 pm - 05:00 pm: Tutorial - “Introduction to Neural Networks with tensorflow, continued”

 

 

Tuesday July 23

10:00 am - 11:00 am: Lecture - “From Neural Networks to Deep Learning”

11:00 am - 11:30 am: Coffee break

11:30 am - 12:30 pm: Lecture - “From Neural Networks to Deep Learning, continued”

12:30 pm - 01:30 pm: Lunch break

01:30 pm - 03:00 pm: Tutorial - “Data-driven Modelling with tensorflow, Part I”

03:00 pm - 03:30 pm: Coffee break

03:30 pm - 05:00 pm: Tutorial - “Data-driven Modelling with tensorflow, Part I, continued”

 

 

Wednesday July 24

10:00 am - 11:00 am: Lecture - “Approximation Theory for Neural Networks”

11:00 am - 11:30 am: Coffee break

11:30 am - 12:30 pm: Lecture - “Approximation Theory for Neural Networks, continued”

12:30 pm - 01:30 pm: Lunch break

01:30 pm - 03:00 pm: Tutorial - “Data-driven Modelling with tensorflow, Part II”

03:00 pm - 03:30 pm: Coffee break

03:30 pm - 05:00 pm: Tutorial - “Data-driven Modelling with tensorflow, Part II, continued"

 

 

Thursday July 25: Mini-workshop: Deep Learning

09:30 am - 10:15 am: Talk 1

10:15 am - 11:00 am: Talk 2

11:00 am - 11:30 am: Coffee break

11:30 am - 12:15 pm: Talk 3

12:15 pm - 01:45 pm: Lunch break

01:45 pm - 02:30 pm: Talk 4

02:30 pm - 03:15 pm: Talk 5

 

 

Confrimed Speakers

Talk 1 - Max Libbrecht (SFU), Understanding human gene regulation using deep neural networks.

Talk 2 - Paul Tupper (SFU), Which Learning Algorithms Can Generalize Identity Effects to Novel Inputs?

Talk 3 - Clayton Webster (University of Tennessee),TBA

Talk 4 - Aaron Berk (UBC), A deep learning approach to retinal fundus imaging.

Talk 5 - Ben Adcock (SFU), Instabilities in deep learning.

 

 

 

This event is part of the PIMS CRG on High Dimensional Data Analysis.

Organizers:

Ben Adcock, SFU

Nicholas Dexter, SFU 

Other Information: 

Location:

Big Data Hub, SFU Burnaby

 

Registration:

Registration for this event is by invitation only. Invited particpants will be required to create a PIMS account and then return to this page to complete their registration.

 

Accommodation:

Accommodation for out of town guests is available here .

 

Applications for Travel Assistance:

Applications for Travel Assistance are now closed.