Data Science Workshop

August 14–25, 2017

Vancouver, BC

About

Targeted at graduate students in the Institute of Applied Mathematics at UBC and students at SFU with similar interests, the 2017 bcdata Data Science Workshop has two goals: to bring together top researchers, industry professionals and BC Math students to tackle interesting research and industry problems; and to develop data science literacy in students with strong mathematical skills who may have little or no previous experience in the realm of “data science”.

This workshop will give students experience with data science tools — such as working with large data sets, statistical inference, and machine learning — that will be helpful in their research, as well as in their career options after graduation. For more information on workshop content, visit the posts section, schedule, or see below for additional information.

Description

Summary

The two-week workshop will include both theoretical and practical components, featuring lectures on the theory of algorithms used in data science and the freeware implementation of these methods. In the first week, data sets from industry and government will be introduced by guest speakers and used as examples data sets for mini-projects. Each data set will lead to a capstone project in the second week.

Computational work will be done with Jupyter notebooks using bcdata.syzygy.ca. Participants will have the opportunity to work with big data, and learn subsequent analysis motifs using machine learning, data clustering, parameter fitting, and other techniques.

There will be a short course in linear algebra and software tools prior to the workshop to cover background material in scientific computing, linear algebra, statistical methods and optimization. For more information, see the pre-workshop description.

See below for a detailed schedule. Lecture notes and workshop materials can be found on the associated GitHub repository.

Projects Overview

There will be several data sets used in the workshop. We will add in the details as they become finalized. For full project/data details, visit the projects section.

Data-driven modeling of video compression
Roger Donaldson, Ph.D. (Midvale Applied Mathematics)
A risk-based platform for accident prevention
Soyean Kim, P.Stat. (BC Safety Authority)
Project Hop: Real-time agriculutural sensing
Nathan Vadeboncoeur (SmartSoil)
Elucidating enhancer-promoter gene expression using ConvNets
Cory Simon, Ph.D. & Wouter Meuleman, Ph.D. (Altius Institute)

Recent Posts

Workshop Information

The 2017 bcdata Data Science Workshop

Fri, Aug 25, 2017 academic, workshop, description, data, science, linear, algebra, scientific, computing

Continue reading for a full description of the workshop, a list of confirmed speakers and mentors, and a list of useful links.

Week 2: Advanced Topics

Mon, Aug 21, 2017 compressed sensing, machine learning, dimension reduction, gene expression, genetics

Information on the material comprising the mornings of the second week. These advanced lecture topics will build on the fundamental tools developed in the first week by demonstrating important applications and generalizations of data science tools.

Career Panel: Mathematicians in Industry

Wed, Aug 16, 2017 career-panel, industry, mathematicians, jobs, career

Join us August 16th at 6:00 PM for a panel discussion and reception, for mathematicians who are contemplating non-academic career options.

Week 1: Mini-project Information

Mon, Aug 14, 2017

Information about the exercises in the first week associated with the morning lecture material.

Week 1: Lecture Syllabus

Mon, Aug 14, 2017 lectures, classification, regression, neural network, first-week, hypothesis testing, experimental design, basic topics

Descriptions of the introductory data science material to be covered in the mornings of the first week. These introductory lecture topics will familiarize participants with domain-specific jargon and concepts, and serve as the starting point of a toolbox for the second-week projects.