Unifying the Mind
Favorite Add to Favorites

Unifying the Mind

Cognitive Representations as Graphical Models

By David Danks

A novel proposal that the unified nature of our cognition can be partially explained by a cognitive architecture based on graphical models.





A novel proposal that the unified nature of our cognition can be partially explained by a cognitive architecture based on graphical models.

Our ordinary, everyday thinking requires an astonishing range of cognitive activities, yet our cognition seems to take place seamlessly. We move between cognitive processes with ease, and different types of cognition seem to share information readily. In this book, David Danks proposes a novel cognitive architecture that can partially explain two aspects of human cognition: its relatively integrated nature and our effortless ability to focus on the relevant factors in any particular situation. Danks argues that both of these features of cognition are naturally explained if many of our cognitive representations are understood to be structured like graphical models.

The computational framework of graphical models is widely used in machine learning, but Danks is the first to offer a book-length account of its use to analyze multiple areas of cognition. Danks demonstrates the usefulness of this approach by reinterpreting a variety of cognitive theories in terms of graphical models. He shows how we can understand much of our cognition—in particular causal learning, cognition involving concepts, and decision making—through the lens of graphical models, thus clarifying a range of data from experiments and introspection. Moreover, Danks demonstrates the important role that cognitive representations play in a unified understanding of cognition, arguing that much of our cognition can be explained in terms of different cognitive processes operating on a shared collection of cognitive representations. Danks's account is mathematically accessible, focusing on the qualitative aspects of graphical models and separating the formal mathematical details in the text.


$42.00 S ISBN: 9780262027991 304 pp. | 9 in x 6 in 24 line drawings


  • This is an interesting and engaging book....Danks has provided one of the few book-length philosophical examinations of a model-based approach to cognition, and this fact is itself enough to make it an important contribution.

    Notre Dame Philosophical Reviews


  • Required reading. A sophisticated and elegant exploration of how we learn and reason about the causal structure of the world and a powerful boost for the fascinating hypothesis that graphical models may be at the very heart of cognition.

    Nick Chater

    Professor of Behavioural Science, Warwick Business School

  • Few philosophers address questions of interest to working scientists. David Danks is one of the few. His ideas about conceptualizing cognitive representations as graphical models have profound implications for all mind–brain investigators. Unifying the Mind could be to this decade what Parallel Distributed Processing was to the 1980s.

    John T. Bruer

    President, James S. McDonnell Foundation

  • This terrific book proposes a unified theory of cognition, showing how a range of different cognitive activities including causal learning, reasoning involving concepts, and decision making can all be understood in terms of graphical models. It is clearly argued and original and insightful throughout. It is one of the very best books of the past decade in the general area of theoretical cognitive psychology and philosophy of psychology.

    James Woodward

    Distinguished Professor, History and Philosophy of Science, University of Pittsburgh

  • This book presents a comprehensive and compelling account of how versatile graphical models are in representing learning, reasoning, and cognition. It will be valuable reading for all students of the mind, especially in machine learning, cognitive science, artificial intelligence, and philosophy of science.

    Judea Pearl

    Professor of Computer Science, Cognitive Systems Lab, University of California, Los Angeles; author of Causality: Models, Reasoning, and Inference