Clustering & Classification (11 of 11): Dimensionality Reduction Techniques (2 of 2)

Data rarely comes neatly labelled or structured, yet patterns still exist—even when they are not immediately obvious. Clustering and classification methods allow researchers to uncover structure in their data, group similar observations, and reduce dimensionality without imposing rigid assumptions about the underlying relationships.

This series introduces researchers to statistical and machine-learning methods for grouping, modelling, and interpreting high-dimensional data. Participants will learn a broad range of approaches—from hierarchical and centroid-based models to probabilistic, fuzzy, density-based, graph-based, and mixed-type clustering techniques—along with strategies for dimensionality reduction and fairness considerations. Emphasis is placed on understanding model assumptions, evaluating model performance, and selecting methods that align with the characteristics of the data rather than forcing data to fit inappropriate models.

All workshops will use R and RStudio, so some experience with R or other programming languages is encouraged but not required. See the R Fundamentals for Data Analysis for an introduction to R and RStudio. Attendees without prior experience are encouraged to review this content.

Dimensionality Reduction Techniques (2 of 2; workshop 11 of 11): This session explores nonlinear and manifold-based methods, including t-SNE and UMAP. We examine their assumptions, visualization strengths, and implications for downstream clustering. Participants will learn to apply these advanced techniques in R and assess their usefulness for revealing complex data structures.

Application: Industrial Sensor & Process Data

REGISTER FOR INDIVIDUAL WORKSHOP

REGISTER FOR ALL WORKSHOPS IN THE SERIES

For a complete list of upcoming CSC Workshops, please visit our workshops page.

This workshop qualifies for the Scholarly Research, Writing, and Publishing Credential offered through the College of Graduate Studies.

Questions? Contact the Centre for Scholarly Communication at csc.ok@ubc.ca.