Conceptual Spaces: The Geometry of Thought” by Peter Gärdenfors offers a unique perspective on cognitive science by presenting a theory of conceptual representations that bridges the gap between the symbolic and connectionist approaches. Gärdenfors argues that an intermediate level of representational content, based on conceptual spaces, can provide solutions to various challenges in cognitive science. This book review aims to provide an overview of Gärdenfors’s work, highlighting key concepts and contributions.
Summary of the Book: Gärdenfors’s theory revolves around the notion of conceptual spaces, which are built upon geometrical structures derived from multiple quality dimensions. The book explores the applications of this theory in concept learning, similarity modeling, and other cognitive phenomena. By focusing on the constructive aspects of cognitive science, Gärdenfors demonstrates how his theory can be utilized in developing artificial systems capable of solving cognitive tasks.
Within cognitive science, two approaches currently dominate the problem of modeling representations. The symbolic approach views cognition as computation involving symbolic manipulation. Connectionism, a special case of associationism, models associations using artificial neuron networks. Peter Gärdenfors offers his theory of conceptual representations as a bridge between the symbolic and connectionist approaches.
Symbolic representation is particularly weak at modeling concept learning, which is paramount for understanding many cognitive phenomena. Concept learning is closely tied to the notion of similarity, which is also poorly served by the symbolic approach. Gärdenfors’s theory of conceptual spaces presents a framework for representing information on the conceptual level. A conceptual space is built up from geometrical structures based on a number of quality dimensions. The main applications of the theory are on the constructive side of cognitive science: as a constructive model the theory can be applied to the development of artificial systems capable of solving cognitive tasks. Gärdenfors also shows how conceptual spaces can serve as an explanatory framework for a number of empirical theories, in particular those concerning concept formation, induction, and semantics. His aim is to present a coherent research program that can be used as a basis for more detailed investigations.