The codelets rely on an associative network, slipnet, built on pre-programmed concepts and their associations (a long-term memory). They create and destroy temporary perceptual constructs, probabilistically trying out variations to eventually produce an answer. High-level perception emerges from the spreading activity of many independent processes, called codelets, running in parallel, competing or cooperating. 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. Alan Brogan.Ĭopycat produces answers to such problems as "abc is to abd as ijk is to what?" (abc:abd :: ijk:?). The latest version in 2018 is a Python3 port by Lucas Saldyt and J. The original Copycat was written in Common Lisp and is bitrotten (as it relies on now-outdated graphics libraries for Lucid Common Lisp) however, Java and Python ports exist. Screenshot of Metacat (Copycat successor) in operation, slightly edited with commentary at bottom.Ĭopycat is a model of analogy making and human cognition based on the concept of the parallel terraced scan, developed in 1988 by Douglas Hofstadter, Melanie Mitchell, and others at the Center for Research on Concepts and Cognition, Indiana University Bloomington.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |