Probabilistic Graphical Modelling and Its Applications
Details
Dear Participant(s),
This two-hour webinar provides an introduction to Probabilistic Graphical Models (PGMs), a powerful framework that integrates probability theory and graph theory to represent and analyze complex systems under uncertainty. The session is designed to equip participants with both conceptual understanding and practical skills for applying PGMs to real-world problems.
Key Topics to be Covered:
- Fundamental Concepts: Bayesian Networks, Markov Random Fields, conditional independence, and the role of PGMs in addressing high-dimensional data challenges.
- Practical Applications: Use cases in healthcare (disease diagnosis and prognosis), finance (fraud detection and risk assessment), and artificial intelligence (natural language processing and decision support systems).
- Hands-on Demonstration: Live implementation in R using packages such as bnlearn and igraph for constructing, visualizing, and performing inference on graphical models.
Learning Outcomes:
By the end of the webinar, participants will:
- Understand the core principles and underlying theory of Probabilistic Graphical Models.
- Appreciate the relevance and applicability of PGMs across diverse domains.
- Acquire foundational skills for implementing and exploring graphical models using R.
Prerequisite: No prior knowledge or experience in graphical modeling is required. The webinar is suitable for students, researchers, academics, data analysts, and professionals interested in statistical modeling, machine learning, and data science.
Date : Thursday, 18th June, 2026
Time : 3:00pm – 5:00pm (WAT)
Venue : Online Platform (Zoom)
Computing Software : R Package (R Studio)
For more detail information, get in touch with us at Osun R User Group, Nigeria:
Emails: [osunrug@gmail.com](mailto:osunrug@gmail.com) Phone: +2348068998580 (WhatsApp Only)
Dr. Timothy A. OGUNLEYE
Founder, Osun R User Group, Nigeria
Personal Websites: https://timothy-ogunleye.vercel.app/ and https://timothy-ogunleye.com.ng/