Causal AI.

Format:

Book

Author/Creator:

Ness, Robert Osazuwa.

Language:

English

Subjects (All):

Artificial intelligence.

Causation.

Computer algorithms.

Physical Description:

1 online resource (421 pages)

Edition:

1st ed.

Place of Publication:

New York : Manning Publications Co. LLC, 2025.

Summary:

Traditional ML models can't answer causal questions like, "Why did that happen?" or, "What factors should I change to get a particular outcome?" This book blends advanced statistical methods, computational techniques, and new algorithms to create machine learning systems that automate the process of causal inference. Causal AI introduces the tools, techniques, and algorithms of cusal reasoning for machine learning. This unique book masterfully blends Bayesian and probabilistic approaches to causal inference with practical hands-on examples in Python. Along the way, you'll learn to integrate causal assumptions into deep learning architectures, including reinforcement learning and large language models. You'll also use PyTorch, Pyro, and other ML libraries to scale up causal inference.

Contents:

Why causal AI

Primer on probabilistic generative modeling

Building a causal graphical model

Testing the DAG with causal constraints

Connecting causality and deep learning

Structural causal models

Interventions and causal effects

Counterfactuals and parallel worlds

General counterfactual inference algorithm

Identification and the causal hierarchy

Building a causal inference workflow

Causal decisions and reinforcement learning

Causality and large language models.

Notes:

Description based on publisher supplied metadata and other sources.

Includes index.

ISBN:

9781638357346

163835734X

OCLC:

1499720463