Conceptual Spaces: The Geometry of Thought by Peter Gärdenfors

By Peter Gärdenfors

Inside cognitive technological know-how, methods presently dominate the matter of modeling representations. The symbolic strategy perspectives cognition as computation regarding symbolic manipulation. Connectionism, a different case of associationism, versions institutions utilizing synthetic neuron networks. Peter Gardenfors deals his concept of conceptual representations as a bridge among the symbolic and connectionist ways. Symbolic illustration is especially vulnerable at modeling notion studying, that is paramount for realizing many cognitive phenomena. proposal studying is heavily tied to the suggestion of similarity, that is additionally poorly served by means of the symbolic process. Gardenfors's conception of conceptual areas provides a framework for representing details at the conceptual point. A conceptual house is equipped up from geometrical buildings in response to a few caliber dimensions. the most functions of the speculation are at the confident part of cognitive technology: as a optimistic version the idea might be utilized to the improvement of synthetic structures in a position to fixing cognitive initiatives. Gardenfors additionally exhibits how conceptual areas can function an explanatory framework for a couple of empirical theories, specifically these touching on notion formation, induction, and semantics. His goal is to provide a coherent study application that may be used as a foundation for extra unique investigations.

Show description

Read or Download Conceptual Spaces: The Geometry of Thought PDF

Similar geometry books

Gems of Geometry

In response to a sequence of lectures for grownup scholars, this energetic and wonderful publication proves that, faraway from being a dusty, boring topic, geometry is in truth jam-packed with good looks and fascination. The author's infectious enthusiasm is positioned to exploit in explaining a few of the key strategies within the box, beginning with the Golden quantity and taking the reader on a geometric trip through Shapes and Solids, in the course of the Fourth size, winding up with Einstein's Theories of Relativity.

Pi: A Source Book

Pi is likely one of the few innovations in arithmetic whose point out conjures up a reaction of popularity and curiosity in these now not involved professionally with the topic. but, regardless of this, no resource ebook on Pi has ever been released. Mathematicians and historians of arithmetic will locate this e-book integral.

Low Dimensional Topology

Derived from a unique consultation on Low Dimensional Topology equipped and performed by means of Dr Lomonaco on the American Mathematical Society assembly held in San Francisco, California, January 7-11, 1981

Extra resources for Conceptual Spaces: The Geometry of Thought

Example text

He asks the following questions: "How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? " Harnad calls this problem the symbol grounding problem. " Thus the symbol grounding problem can be argued to be an artifact of the symbolic position. In the same vein, Stewart (1996, 323) says: 48 [S]ince linguistic symbols emerge from the precursors of the semiotic signals of animal communication, they always already have meaning, even before they acquire the status of symbols.

On this view, formal symbols devoid of meaning are derivative, being obtained by positively divesting previously meaningful symbols of their significance. Quite concretely, this process occurred historically in the course of the history of axiomatic mathematics from Euclid to Hilbert. From this point of view, the "symbol-grounding problem" of computation cognitive science looks rather bizarre and somewhat perverse: why go to all the bother of divesting "natural symbols" of their meaning, and then desperately trying to put it back, when it would seem so simple to leave them as they are!

2 The Limitations of Symbolic Representations After outlining this position, I now turn to the limitations of the representational power of the symbolic approach. One of the major problems encountered in the classical form of AI is the frame problem (McCarthy and Hayes 1969, Dennett 1987, Janlert 1987). Within the early AI community, it was hoped that if we could represent the knowledge necessary to describe the world and the possible actions in a suitable symbolic formalism, then by coupling this world description with a powerful inference machine one could construct an artificial agent capable of planning and problem solving.

Download PDF sample

Rated 4.18 of 5 – based on 35 votes