Unifying the Mind ― Cognitive Representations As Graphical Models

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

The computational framework of graphical models is widely usedin machine learning, but Danks is the first to offer a book-length account of its use to analyzemultiple areas of cognition. Danks demonstrates the usefulness of this approach by reinterpreting avariety of cognitive theories in terms of graphical models. He shows how we can understand much ofour 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 andintrospection. Moreover, Danks demonstrates the important role that cognitive representations playin a unified understanding of cognition, arguing that much of our cognition can be explained interms of different cognitive processes operating on a shared collection of cognitiverepresentations. Danks's account is mathematically accessible, focusing on the qualitative aspectsof graphical models and separating the formal mathematical details in the text.

David Danks is Professor of Philosophy and Psychology at Carnegie Mellon University.