Fluid Concepts and Creative Analogies
Douglas Hofstadter

bdbs commerce | beta


Softcover: 528 pages
Publisher: Basic Books; Edition 1 (March 22, 1996)
Language: English
ISBN-10: 0465024750
ISBN-13: 978-0465024759
Physical Trim: 9.8 x 7.3 x 1.2 inches

Fluid Concepts and Creative Analogies
Douglas Hofstadter

bdbs commerce | beta


Fluid Concepts and Creative Analogies

Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought is a 1995 book by Douglas Hofstadter and other members of the Fluid Analogies Research Group exploring the mechanisms of intelligence through computer modeling. It contends that the notions of analogy and fluidity are fundamental to explain how the human mind solves problems and to create computer programs that show intelligent behavior. It analyzes several computer programs that members of the group have created over the years to solve problems that require intelligence. Readers of earlier works by Hofstadter will find this book a natural extension of his style and his ideas about creativity and analogy; in addition, psychologists, philosophers, and artificial-intelligence researchers will find in this elaborate web of ingenious ideas a deep and challenging new view of mind.

The book is a collection of revised articles that appeared in precedence, each preceded by an introduction by Hofstadter. They describe the scientific work by him and his collaborators in the 1980s and 1990s. The project started in the late 1970s at Indiana University, where Hofstadter collaborated with Marsha Meredith and Gray Clossman. In 1983 he took a sabbatical year at MIT, working in Marvin Minsky's Artificial Intelligence Lab. There he met and collaborated with Melanie Mitchell, who subsequently did her Ph.D. with him, David Rogers, and Marek Lugowski. Subsequently Hofstadter moved to the University of Michigan, where the FARG (Fluid Analogies Research Group) was founded. Eventually he returned to Indiana University in 1988, continuing the FARG research there. The book was written during a sabbatical year at the Istituto per la Ricerca Scientifica e Tecnologica in Trento, Italy.

About the Author

Douglas R. Hofstadter was born in New York in 1945. He is an American academic whose research focuses on consciousness, thinking and creativity. His publications include Metamagical Themas, Fluid Concepts and Creative Analogies, Le Ton beau de Marot: In Praise of the Music of Language, Eugene Onegin: A Novel Versification and I Am a Strange Loop. He is best known for Godel, Escher, Bach: an Eternal Golden Braid, first published in 1979, for which he was awarded the 1980 Pulitzer Prize for general non-fiction.

Chapters and Authors

  • To Seek Whence Cometh a Sequence (D.H.)
  • The Architecture of Jumbo (D.H.)
  • Numbo: A Study in Cognition and Recognition (Daniel Defays)
  • High-level Perception, Representation, and Analogy: A Critique of Artificial-intelligence Methodology (David Chalmers, Robert French, and D.H.)
  • The Copycat Project: A Model of Mental Fluidity and Analogy-making (D.H. and Melanie Mitchell)
  • Perspectives on Copycat: Comparisons with Recent Work (Melanie Mitchell and D.H.)
  • Prolegomena to Any Future Metacat (D.H.)
  • Tabletop, BattleOp, Ob-Platte, Potelbat, Belpatto, Platobet (D.H. and Robert French)
  • The Emergent Personality of Tabletop, a Perception-based Model of Analogy-making (D.H. and Robert French)
  • Letter Spirit: Esthetic Perception and Creative Play in the Rich Microcosm of the Roman Alphabet (D.H. and Gary McGraw)

  • Summary of Chapters

    To Seek Whence Cometh a Sequence

    The first AI project by Hofstadter stemmed from his teenage fascination with number sequences. When he was 17, he studied the way that triangular and square numbers interleave, and eventually found a recursive relation describing it. In his first course on AI, he set to the students and to himself the task of writing a program that could extrapolate the rule by which a numeric sequence is generated. He discusses breadth-first and depth-first techniques, but eventually concludes that the results represent expert systems that incarnate a lot of technical knowledge but don't shine much light on the mental processes that humans use to solve such puzzles.

    Instead he devised a simplified version of the problem, called SeekWhence, where sequences are based on very simple basic rules not requiring advanced mathematical knowledge. He argues that pattern recognition, analogy, and fluid working hypotheses are fundamental to understand how humans tackle such problems.

    The Architecture of Jumbo
    Jumbo is a program to solve jumbles, word puzzles consisting in five or six scrambled letters that need to be anagrammed to form an English word. The resulting word does not need to be a real one but just to a plausible, that is, to consists of a sequence of letters that is normal in English.

    The constituent elements of Jumbo are the following:

  • The "chunkabet": a database of chunks, small sequences of letters, with a numeric value giving their strength as possible components of a word.
  • The "cytoplasm": a loose data structure containing partial associations of letter, modeling a form of working memory. The name is inspired by the place in a cell where molecular fragments are assembled into proteins.
  • The "Coderack": a structure containing "codelets", small pieces of programs that are waiting to be executed in the cytoplasm; the codelet that is executed next is chosen non-deterministically, based on urgencies attached to them; a codelet may form new associations, break down old ones, or generate more codelets.
  • A "temperature" is associated to the present state of the cytoplasm; it determines how probable it is that a destructive codelet is executed. There is a "freezing" temperature at which no destruction can occur anymore: a solution has been found.

    Numbo: A Study in Cognition and Recognition

    Numbo is a program by Daniel Defays that tries to solve numerical problems similar to those used in the French game "Le compte est bon". The game consists in combining some numbers called "bricks", using the operations of multiplication, addition, and subtraction, to obtain a given result.

    The program is modeled on Jumbo and Copycat and uses a permanent network of known mathematical facts, a working memory in the form of a cytoplasm, and a coderack containing codelets to produce free associations of bricks in order to arrive at the result.

    Highlevel Perception, Representation, and Analogy

    The subtitle A Critique of Artificial-intelligence Methodology indicates that this is a polemical article, in which David Chalmers, Robert French, and Hofstadter criticize most of the research going on at that time (the early '80s) as exaggerating results and missing the central features of human intelligence.

    Some of these AI projects, like the structure mapping engine (SME), claimed to model high faculties of the human mind and to be able to understand literary analogies and to rediscover important scientific breakthroughs. In the introduction, Hofstadter warns about the Eliza effect that lead people to attribute understanding to a computer program that only uses a few stock phrases. The authors claim that the input data for such impressive results are already heavily structured in the direction of the intended discovery and only a simple matching task is left to the computer.

    Their main claim is that it is impossible to model high-level cognition without at the same time modeling low-level perception. While cognition is necessarily based on perception, they argue that it in turn influences perception itself. Therefore, a sound AI project should try to model the two together. In a slogan repeated several times throughout the book: cognition is recognition.

    Since human perception is too complex to be model by available technology, they favor the restriction of AI projects to limited domains like the one used for the Copycat project.

    The Copycat Project

    This chapter presents, as stated in the full title, A Model of Mental Fluidity and Analogy-making. It is a description of the architecture of the Copycat program, developed by Hofstadter and Melanie Mitchell. The field of application of the program is a domain of short alphabetic sequences. A typical puzzle is: If abc were changed to abd, how would you change ijk in the same way?. The program tries to find an answer using a strategy supposedly similar to the way the human mind tackles the question.

    Copycat has three major arents:

  • The Slipnet , a model of long-term memory in humans. It contains concepts of various degrees of abstraction, from the letter types to the notion of opposite. Concepts are connected with links indicating their similarity. The activation of a node may cause the activation of a neighbor with a probability proportional to the inverse of the length of their link. The length of the links are not static; they have a value at the beginning but the may change elastically during computation according to the partial results achieved.
  • The Workspace , a model of short-term memory. Here partial structures are constructed and dismantled. The temporary results may cause the activation of concepts in the slipnet. A temperature measures the satisfaction of the program with the structure obtained at each moment. High temperature means dissatisfaction and leads to the adoption of a different strategy. Low temperature means satisfaction and the continuation of the present strategy.
  • The Coderack , a collection of codelets, that is small fragments of code, that wait to be selected and executed in the workspace. Each has a weight associated to it that determined its probability to be selected for execution.
  • The resulting software displays emergent properties. It works according to a parallel terraced scan that runs several possible processes at the same time. It shows mental fluidity in that concepts may slip into similar ones. It emulates human behavior in tending to find the most obvious solutions most of the time but being more satisfied (as witnessed by low temperature) by more clever and deep answers that it finds more rarely.

    Perspectives on Copycat

    This chapter compares Copycat with other recent (at the time) work in artificial intelligence. Specifically, it matches it with the claimed results from the structure mapping engine SME and the Analogical Constraint Mapping Engine (ACME). The authors' judgment is that those programs suffer from two defects: Their input is pre-structured by the developers to highlight the analogies that the software is supposed to find; and the general architecture of the programs is serial and deterministic rather than parallel and stochastic like Copycat's, which they consider psychologically more plausible.

    Severe criticism is put on the claim that these tools can solve "real-life" problems. In fact, only the terms used in the example suggest that the input to the programs comes from a concrete situation. The logical structures don't actually imply any meaning for the term.

    Finally a more positive assessment is given to two other projects: Indurkhya' PAN model and Kokinov's AMBR system.

    Prolegomena to Any Future Metacat

    This chapter looks at those aspects of human creativity that are not yet modeled by Copycat and lays down a research plan for a future extension of the software. The main missing element is the mind's ability to observe itself and reflect on its own thinking process. Also important is the ability to learn and to remember the results of the mental activity.

    The creativity displayed in finding analogies should be applicable at ever higher levels: making analogies between analogies (expression inspired by the title of a book by Stanis'aw Ulam), analogies between these second-order analogies, and so on.

    Tabletop, BattleOp, Ob-Platte, Potelbat, Belpatto, Platobet

    Another of Hofstadter's students, Robert French, was assigned the task of applying the architecture of Copycat to a different domain, consisting in analogies between objects lying on a table in a coffeehouse. The resulting program was named Tabletop.

    The authors present a different and vaster domain to justify the relevance of attacking such a trivial-seeming project. The alternative domain is called Ob-Platte and consists in discovering analogies between geographical locations in different regions or countries.

    Once again arguments are offered against a brute-force approach, which would work on the small Tabletop domain but would become unfeasible on the larger Ob-Platte domain. Instead a parallel non-deterministic architecture is used, similar to the one adopted by the Copycat project. The Emergent Personality of Tabletop, a Perception-based Model of Analogy-making

    In the premise to the chapter, title The Knotty Problem of Evaluating Research, Hofstadter considers the question of how research in AI should be assessed. He argues against a strict adherence to a match between the results of an AI program with the average answer of human test subjects. He gives two reasons for his rejection: the AI program is supposed to emulate creativity, while an average of human responses will delete any original insight by any of the single subjects; and the architecture of the program should be more important that its mere functional description.

    In the main article, the architecture of Tabletop is described: it is strongly inspired by that of Copycat and consists of a Slipnet, a Workspace, and a Corerack.

    Letter Spirit

    This last chapter is about a more ambitious project that Hofstadter started with student Gary McGraw. The microdomain used is that of grid fonts: typographic alphabets constructed using a rigid system of small rigid components. The goal is to construct a program that, given only a few or just one letter from the grid font, can generate the whole alphabet in the same style. The difficulty lies in the ambiguity and undefinability of style. The projected program would have a structure very similar to that of Jumble, Numble, Copycat, and Tabletop.


    In the concluding part of the book, Hofstadter analyses some AI projects with a critical eye. He finds that today's AI is missing the gist of human creativity and is making exaggerated claims. The project under scrutiny are the following.

    AARON, a computer artist that can draw images of people in outdoor settings in a distinctive style reminiscent of that of a human artist; criticism: the program doesn't have any understanding of the objects it draws, it just uses some graphical algorithms with some randomness thrown in to generate different scenes at every run and to give the style a more natural feel.

    Racter, a computer author that wrote a book entitled The Policeman's Beard Is Half Constructed. Although some of the prose generated by the program are quite impressive, due in part to the Eliza effect, the computer does not have any notion of plot or of the meaning of the words it uses. Furthermore, the book is made up of selected texts from thousands produced by the computer over several years.

    AM, a computer mathematician that generates new mathematical concepts. It managed to produce by itself the notion of prime number and the Goldbach conjecture. As with Racter, the question is how much the programmer filtered the output of the program, keeping only the occasional interesting output. Also, mathematics being a very specialized domain, it is doubtful whether the techniques used can be abstracted to general cognition.

    Another mathematical program, called Geometry, was celebrated for making an insightful discovery of an original proof that an isosceles triangle has equal base angles. The proof is based on seeing the triangle in two different ways. However, the program generates all possible ways of seeing the triangle, not even knowing that it is the same triangle.

    Hofstadter concludes with some methodological remarks on the Turing Test. In his opinion it is still a good definition and he argues that by interacting with a program, a human may be able to have insight not just on its behaviour but also on its structure. However, he criticises the use that is made of it at present: it encourages the development of fancy natural-language interfaces instead of the investigation of deep cognitive faculties.

    Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nullam placerat, velit at volutpat vestibulum, est mauris interdum nisi, ut lobortis mauris nunc vel elit. Praesent vel massa elit. In et dui odio. Aenean pharetra augue eget arcu eleifend laoreet. Nulla vel neque sed arcu rhoncus pharetra. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce tortor est, faucibus a suscipit eu, accumsan eget dolor. Aliquam nibh metus, lacinia sit amet feugiat non, gravida nec velit. Quisque accumsan enim eget odio pellentesque tempus. Vestibulum dictum iaculis velit sit amet feugiat.

    Phasellus in massa vel ante fermentum venenatis ut nec dui. Proin mollis fermentum blandit. Ut dignissim aliquam neque, eu hendrerit justo bibendum in. Nulla at est vitae quam placerat sagittis et at orci. Aliquam quis urna eget nibh sodales vulputate. Sed hendrerit mattis viverra. Fusce metus est, mattis at mollis nec, mollis vel justo. Nam egestas ultrices tortor, a pellentesque nunc lacinia sit amet. Vestibulum non sapien neque. Nulla blandit felis quis augue viverra faucibus ac non mauris.

    Lorem ipsum dolor sit amet, consectetur adipiscing elit. Cras sodales leo vitae nibh cursus ullamcorper. Sed gravida mauris ac nisi posuere vel tempus sem mattis. Quisque vitae sem arcu, ac hendrerit lacus. Donec pharetra ipsum ac velit feugiat commodo. Suspendisse condimentum vehicula justo et tincidunt. Praesent iaculis venenatis elit, nec suscipit tortor rutrum in. Curabitur augue neque, elementum eu fermentum et, ullamcorper mollis risus. Ut cursus vestibulum blandit. Donec cursus porta libero, a fringilla turpis egestas ut. Lorem ipsum dolor sit amet, consectetur adipiscing elit.

    Vivamus orci sapien, pretium ac tincidunt vitae, vestibulum eu enim. Cras congue nisi quis quam consectetur consequat sed ut neque. Mauris id diam lacus, sed gravida quam. Fusce a pretium quam. Duis gravida aliquam cursus. Nam vel elementum metus. Phasellus dapibus, arcu id egestas eleifend, urna ante sagittis leo, ut consectetur nisi justo cursus nibh. Aliquam porttitor, lectus nec placerat sollicitudin, mi magna pellentesque sem, quis porttitor urna risus quis metus. Proin dignissim sollicitudin leo, nec fringilla tellus volutpat a. Curabitur velit ante, molestie et facilisis in, tincidunt sit amet sapien. Sed at odio risus, in blandit est. Phasellus tempus, ante sed venenatis suscipit, diam velit vehicula turpis, in placerat lectus tortor non turpis. Fusce a dolor non diam egestas feugiat sed et nisi. Sed ullamcorper elit ac nibh semper vel vestibulum nunc ultrices. Integer varius mi id dolor malesuada vitae ullamcorper libero varius. Duis et orci eros. Maecenas nibh urna, faucibus quis luctus nec, fringilla in nulla. Pellentesque vel massa ligula, sed convallis elit. Proin sapien urna, suscipit ac fringilla hendrerit, vulputate id odio. Phasellus dignissim convallis neque, id lobortis libero vehicula vitae.

    Integer urna dolor, semper nec mattis a, suscipit in diam. Nulla tempor enim nisl, ut mollis nisl. Nulla sit amet metus ut enim consequat fermentum. Mauris sed felis urna. Mauris ac nibh lectus, nec lobortis leo. Suspendisse potenti. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia Curae; Praesent molestie pretium dolor, vel consequat odio varius sit amet. Vestibulum scelerisque feugiat neque, nec sollicitudin turpis faucibus a. Donec eget neque ut purus lobortis congue. Fusce eleifend convallis ipsum, at laoreet dolor dictum ac. Maecenas sed nunc risus. Morbi porta ligula varius leo volutpat sit amet porttitor quam eleifend. Ut iaculis blandit tincidunt. Nullam volutpat, magna at sodales ornare, ligula odio semper neque, adipiscing rhoncus felis leo quis ipsum. Quisque leo orci, ultricies sed lacinia et, volutpat a metus. Aliquam facilisis dapibus lorem, ut scelerisque felis aliquam vitae.

    Praesent ligula diam, adipiscing ac congue et, aliquam quis justo. Mauris elementum massa sed libero fermentum vulputate. Ut ligula velit, tincidunt nec scelerisque ac, tincidunt in metus. Vivamus rhoncus nibh ut orci blandit eu varius mi tincidunt. Nulla facilisi. Nunc cursus est in libero rhoncus tincidunt varius enim luctus. Praesent at est mauris. Mauris venenatis dapibus turpis, ut aliquet quam laoreet sit amet. Praesent volutpat, dolor sit amet interdum vulputate, nulla urna pellentesque leo, aliquam accumsan tellus arcu eu leo. Vivamus eget dolor sed sem fringilla rutrum sit amet at augue. Donec hendrerit ipsum vel eros placerat nec dictum ligula dignissim. Vestibulum euismod aliquet tristique. Nam nec mi et elit lobortis interdum. Nulla facilisi. Integer a urna dolor, id suscipit augue. Nullam scelerisque porta lectus, sit amet pellentesque massa tristique et. Donec gravida tincidunt diam vitae tincidunt. Quisque ac turpis sit amet dui consequat ultrices. Maecenas rutrum rutrum magna ut bibendum.

    Sed nisl felis, semper eu dapibus non, commodo vitae leo. Nulla at tellus et ligula faucibus adipiscing. Quisque vitae nunc vitae lectus varius porttitor. Duis ut lorem lorem, id mollis sapien. Proin ullamcorper diam id lacus dictum facilisis. Donec porttitor dolor ut mauris viverra rhoncus. Maecenas aliquam magna quis nisl faucibus quis congue nulla molestie. Praesent semper condimentum massa id sollicitudin. Donec mollis rhoncus sapien id molestie. Cras sagittis commodo suscipit. Nullam non nibh in leo aliquam facilisis. Fusce mollis ornare tristique. Donec ultricies condimentum imperdiet. Phasellus tincidunt diam quis elit pharetra laoreet.

    Etiam sodales lacus accumsan metus aliquet volutpat ornare enim tempor. Curabitur ac venenatis nulla. Duis condimentum nibh vel sem vestibulum a euismod enim luctus. Duis id leo non dolor lobortis venenatis. Quisque a nulla dolor. Mauris pellentesque dignissim suscipit. Duis dictum tristique pellentesque. Aliquam ornare augue eu nulla rutrum et pretium nibh fermentum. Donec vitae nisi arcu. Proin volutpat urna at enim facilisis nec ornare diam rhoncus.

    Integer porttitor, augue non volutpat feugiat, elit ante adipiscing quam, ut scelerisque erat augue quis nisl. In hac habitasse platea dictumst. Etiam sed magna sit amet sem fringilla condimentum. Aliquam in purus sit amet nunc venenatis varius vitae et libero. Fusce ut ornare mi. Quisque lacus mi, egestas eu volutpat ac, vehicula id risus. Mauris venenatis suscipit lacus, et vehicula libero rutrum sit amet. Sed at nibh nisl. Class aptent taciti sociosqu ad litora torquent per conubia nostra, per inceptos himenaeos. Proin elit quam, aliquam quis faucibus nec, egestas eget nisl. Vivamus libero arcu, vulputate ut porttitor scelerisque, lacinia auctor turpis. Maecenas id mi et nibh scelerisque molestie. Phasellus ornare, justo eu porta lobortis, sem arcu congue justo, vel pulvinar urna felis ut nisi. Morbi sapien nibh, aliquam a placerat quis, euismod vel risus. Etiam imperdiet varius metus a aliquet. Nullam eget mi vel turpis convallis consequat. Quisque ornare, neque in gravida dignissim, turpis risus dapibus elit, in ultricies ipsum arcu eu nisl. Fusce elementum elit eu lacus euismod eget laoreet metus fermentum. Ut ac felis in urna pellentesque luctus. Nulla odio elit, cursus vitae imperdiet non, pretium vitae felis. Curabitur facilisis, diam sed scelerisque consequat, eros elit faucibus purus, ut vulputate magna ligula vel mi.

    Nulla dapibus ornare nisi, et dignissim risus tincidunt nec, etc...