the Open Data Science Conference gathers attendees, presenters, and companies that are shaping the present and future of AI and data science. ODSC hosts one of the largest gatherings of professional data scientists, with major conferences in the USA, Europe, and Asia.
Tobacco Dock, London
ODSC Europe: from in-person sessions to digital experiences available to everyone. The hybrid ODSC Europe Conference combines small immersive in-person sessions and hands-on training with innovative and insightful virtual ones.
causaLens’ Andre Franca will be speaking on “From correlation to causality in AI”
In this session, we will present a brief introduction to causality in AI. We will start with fundamental statistics, introduce causal graphs, do-calculus, and general methods for causal inference. We will give an overview of methods that allow the discovery of causal structures from observational data, as well as several applications in business settings. This session will cover topics from the very basic (what is a correlation?) to more complex ideas such as causal representation learning. This is meant to serve as a general and practical overview of the fastest-growing research area in AI.
Overview:
* Pearson to Pearl: A brief intro to causality and statistics
— What are correlations,
— Measuring Association vs measuring causal strength
— Causal Graphs and structural causal equations
— Structural causal equations
* Discovering causality
— Conditional independence
— The chicken and the egg problem
— Basic causal discovery algorithms
* Applications
— Why should you care about causality?
— Simpson’s paradoxes everywhere
— Asking counterfactual questions
— Recourse
— Optimization
* The future of AI
