Advanced Data Science Training I (Fall 2018-Winter 2019) [Closed]

Event Phone: 819-816-3150

Class size limit has been reached — new registrations will be sent to the waiting list.

Length: 20 x 3 hour sessions, weekly, at Transport Canada.
Level: Halfway between a university course and the Applied Data Science and Visualization Training courses.

An introduction to Data Science, data analysis, and data understanding, with topics selected from:

1. Data Science Prerequisites
   Theory: 8 hours, Practice: 7 hours — universals of data science; basics of R/Python; data cleaning; data reduction; case studies
2. Data Visualization
   Theory: 5 hours, Practice: 1 hour — simple graphical methods, representations of multi-dimensional data, design suggestions
3. Introduction to Machine Learning
   Theory: 13 hours, Practice: 5 hours — association rules, decision trees, k-means, issues and challenges, naïve Bayes, hierarchical clustering
4. Text Mining and Natural Language Processing
   Theory: 8 hours, Practice: 4 hours — basics, classification, clustering, sentiment analysis, named-entity recognition, summarization, topic modeling, etc.
5. Focus on Supervised and Unsupervised Learning
   Theory: 6 hours, Practice: 3 hours — density-based clustering, spectral clustering, validation metrics, support vector machines, neural networks, etc.

The goal of this workshop is to provide an introduction to various concepts and algorithms used in A.I. and Data Science, as used in common programming environments. The application of these concepts will be illustrated through some examples ranging from simple to elaborate, along with discussions of common challenges and pitfalls.

There will be a combination of traditional lectures with Jupyter notebook exercises.

Audience and Requirements: This workshop is for individuals who wish to understand the functionality and capabilities offered by different data science concepts and methods, even if they won’t be the ones implementing them. This workshop requires very little mathematical or computer programming knowledge. Some experience with quantitative ideas is assumed. Necessary concepts will be introduced in the course.

Participants must provide a laptop with wi-fi connectivity and the ability to run R/Python notebooks from a web browser (typically, Chrome, Firefox, Edge. Some issues have been encountered with Internet Explorer and the WebSockets driver). Exposure to programming (R/Python/SAS/etc.) a plus.

Expectations: 60 hours of additional independent learning outside of class; suggested readings and exercises