Hofstadter has developed a sophisticated vision of the mind in which perception, at an abstract level, is the key.

Hosftadter and his colleagues at The Fluid Analogies Research Group have developed computer models that help describe and explain human discovery, creation and analogical thought. The key issue of perception is investigated through the exploration of playful anagrams, number puzzles, word play and fanciful alphabetical styles, and the result is a survey of cognitive processes. This text presents the results.

Describes research projects in cognitive science over the past twenty years, and discusses arithmetical play, analogy, research evaluation, and creativity

Shows how analogy-making pervades human thought at all levels, influencing the choice of words and phrases in speech, providing guidance in unfamiliar situations, and giving rise to great acts of imagination.

Argues that the key to understanding ourselves and consciousness is the "strange loop," a special kind of abstract feedback loop that inhabits the brain.

The psychologist William James observed that "a native talent for perceiving analogies is... the leading fact in genius of every order." The centrality and the ubiquity of analogy in creative thought have been noted again and again by scientists, artists, and writers, and understanding and modeling analogical thought have emerged as two of the most important challenges for cognitive science.Analogy-Making as Perception is based on the premise that analogy-making is fundamentally a high-level perceptual process in which the interaction of perception and concepts gives rise to "conceptual slippages" which allow analogies to be made. It describes Copycat - a computer model of analogymaking, developed by the author with Douglas Hofstadter, that models the complex, subconscious interaction between perception and concepts that underlies the creation of analogies.In Copycat, both concepts and high-level perception are emergent phenomena, arising from large numbers of low-level, parallel, non-deterministic activities. In the spectrum of cognitive modeling approaches, Copycat occupies a unique intermediate position between symbolic systems and connectionist systems a position that is at present the most useful one for understanding the fluidity of concepts and high-level perception.On one level the work described here is about analogy-making, but on another level it is about cognition in general. It explores such issues as the nature of concepts and perception and the emergence of highly flexible concepts from a lower-level "subcognitive" substrate.Melanie Mitchell, Assistant Professor in the Department of Electrical Engineering and Computer Science at the University of Michigan, is a Fellow of the Michigan Society of Fellows. She is also Director of the Adaptive Computation Program at the Santa Fe Institute.