From Data to Decisions Under Uncertainty: Modern Bayesian Computing with PyMC

Welcome to our Montreal AI ML Meetup, an informal gathering where enthusiasts, developers, and AI scientists converge to discuss the rapidly evolving world of Artificial Intelligence and Machine Learning!

Join Our Discord: https://discord.gg/7t7d8pngeZ

What to Expect:

For this event, we will have Christopher Fonnesbeck, core developer of PyMC, present PyMC and show us how to use it to calculate uncertainties.

Location : Deck HQ, 180 Peel Street, Montreal

Schedule:

17:30 : Door open
18:00 : Presentation
19:00 : Networking

Speaker : Christopher Fonnesbeck

Chris is a Principal Quantitative Analyst at PyMC Labs and an Adjoint Associate Professor at the Vanderbilt University Medical Center, with 20 years of experience as a data scientist in academia, industry, and government, including 7 years in pro baseball research with the Philadelphia Phillies, New York Yankees, and Milwaukee Brewers. He is interested in computational statistics, machine learning, Bayesian methods, and applied decision analysis. He hails from Vancouver, Canada and received his Ph.D. from the University of Georgia.​​

From Data to Decisions Under Uncertainty: Modern Bayesian Computing with PyMC:

Traditional machine learning models excel at making predictions but often fall short when quantifying uncertainty—a critical requirement for high-stakes decisions in production systems. This talk introduces PyMC, a probabilistic programming framework for Python, demonstrating how modern Bayesian methods can enhance your ML toolkit with built-in uncertainty quantification and interpretable results. We'll begin by demystifying Bayesian computation through live coding examples, showing how PyMC makes it as easy to code probabilistic models as writing them on a whiteboard. Once specified, models can be compiled to a high-performance back end like JAX or Numba, and fit using one of several modern inference methods. I will cover key features like PyMC's coords and dims system that prevents dimensionality bugs, `pymc.Data` containers for production model updates, and functions `pymc.do()` and `pymc.observe()` for facilitating causal inference workflows. You'll learn the complete Bayesian workflow—from prior specification through model validation—with emphasis on practical implementation over mathematical theory.

For Whom Is This Meetup:

• Developers and scientists interested in AI/ML.
• Tech enthusiasts keen on the latest industry trends.
• Professionals are looking to network in the AI/ML field.
• Anyone curious about the technological aspects of AI/ML.

Important Notes:

• Open Dialogue: Feel free to discuss your experiences and learnings, but please refrain from disclosing confidential information related to ongoing projects or sensitive company data.
• Respectful Networking: Job-seeking and hiring conversations are welcome, but we encourage respect and professionalism in all interactions.

Join Us:

Whether you're a seasoned professional or just curious about AI/ML, our meetup offers a unique opportunity to connect, learn, and grow. Let’s share our passion for technology and pave the way for innovation!
RSVP Now! Limited spots are available.
We look forward to seeing you there and exploring the dynamic world of AI and ML together!