Copycat (software)
Copycat is a
model of
analogy making and human
cognition based on the concept of the
parallel terraced scan, developed by
Douglas Hofstadter,
Melanie Mitchell, and others at the at
Center for Research on Concepts and Cognition,
Indiana University Bloomington.
Copycat produces answers to such problems as "abc is to abd as xyz is to what?" (abc:abd :: xyz:?). Hofstadter and Mitchell consider analogy making as the core of high-level cognition, or
high-level perception, as Hofstadter calls it, basic to recognition and categorization. High-level perception
emerges from the spreading activity of many independent processes, called
codelets, running in parallel, competing or cooperating. They create and destroy temporary perceptual constructs, probabilistically trying out variations to eventually produce an answer. The codelets rely on an associative network,
slipnet, built on pre-programmed concepts and their associations (a
long-term memory). The changing activation levels of the concepts make a conceptual overlap with neighboring concepts.
Copycat's architecture is tripartite, consisting of slipnet, a
working area (also called
working memory), and the coderack (with the codelets). The slipnet is a network comprised of nodes, which represent permanent concepts, and links, which are relations, between them. The codelets increase activations in the slipnet, and build structures, based on the associations there, in the working area.
Copycat differs considerably in many respects from other
cognitive architectures such as
ACT-R,
Soar,
DUAL,
Psi, or
subsumption architectures.
Copycat is Hofstadter's most popular model. Other models presented by Hofstadter et al. before Copycat were similar in architecture, but different in the so-called micro-domain, their application, e.g. Letter-spirit, etc.
*
*
a short description of Copycat*
Beyond Copycat: Incorporating Self-Watching into a Computer Model (pdf)
*
How to get the source code
