Sebastian Raschka
Description A deep dive into the architecture and implementation of AI models capable of logical deduction and multi-step reasoning. It explains how t...
Robert Osazuwa Ness
Publisher
Simon and Schuster
Published
5
Duration
15 hr 24 min
ISBN
9781633439917
Genres
Description An introduction to building AI models that identify and reason about cause-and-effect relationships rather than just statistical correlations. It introduces the "Causal Hierarchy" and how to apply it to machine learning workflows.Key Topics: Structural Causal Models (SCM), do-calculus, counterfactual reasoning, and causal discovery algorithms. About the Technology: Causal inference allows AI to answer "what if" questions, making models more robust, explainable, and useful for decision-making. About the Book: Uses a code-first approach with Python libraries (like PyTorch and DoWhy) to implement causal logic in predictive models. About the Reader: For data scientists and AI engineers who want to build more interpretable and reliable models for business or scientific use. About the Author: Robert Osazuwa Ness is a researcher at Microsoft Research specializing in causal machine learning and probabilistic programming.
