Abstract
A theory of general intelligence must account for how an intelligent agent can map percepts into actions at the level of human performance. We describe a new approach to this percept-to-action mapping. Our approach is based on four ideas: the world exhibits fractal self-similarity at multiple scales, the design of mind reflects the design of the world, similarity and analogy form the core of intelligence, and fractal representations provide a powerful technique for perceptual similarity and analogy. We divide our argument into two parts. In the first part, we describe a technique of fractal analogies and show how it gives human-level performance on an intelligence test called the Odd One Out. In the second, we describe how the fractal technique enables the percept-to-action mapping in a simple, simulated world.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arkin, R.: Behavior-Based Robotics. The MIT Press, Boston (1998)
Barnsley, M., Hurd, L.: Fractal Image Compression. A.K. Peters, Boston (1992)
Biederman, I.: Recognition-by-Components: A Theory of Human Image Understanding. Psychological Review 94, 115–147 (1987)
Davis, R., Shrobe, H., Szolovits, P.: What is a Knowledge Representation? AI Magazine 14(1), 17–33 (1993)
Davies, J., Goel, A.: Visual Analogy in Problem Solving. In: Proc. 17th International Joint Conference on Artificial Intelligence, IJCAI 2001, pp. 377–382. Morgan Kaufmann (August 2001)
Davies, J., Goel, A., Yaner, P.: Proteus: Visuospatial Analogy in Problem Solving. Knowledge-Based Systems 21(7), 636–654 (2008)
Davies, J., Goel, J., Nersessian, N.: A Computational Model of Visual Analogies in Design. Cognitive Systems Research 10, 204–215 (2009)
Davies, J., Nersessian, N., Goel, A.: Visual Models in Analogical Problem Solving. Foundations of Science 10(1), 133–152 (2005)
Diascro, M.N., Brody, N.: Odd-man-out and intelligence. Intelligence 19(1), 79–92 (1994)
Gentner, D.: Structure-Mapping: A Theoretical Framework for Analogy. Cognitive Science 7(2), 155–170 (1983)
Hampshire, A.: The Odd One Out Test of Intelligence (2010), http://www.cambridgebrainsciences.com/browse/reasoning/test/oddoneout
Haugeland, J. (ed.): Mind Design: Philosophy, Psychology and Artificial Intelligence. MIT Press (1981)
Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.: Image analogies. Computer Graphics 25(4), 327–340 (2001) (SIGGRAPH 2001 Conference Proceedings)
Hofstadter, D., Fluid Analogies Research Group (eds.): Fluid concepts & creative analogies: Computer models of the fundamental mechanisms of thought. Basic Books, New York (1995)
Indurkhya, B.: On creation of features and change of representation. Journal of Japanese Cognitive Science Society 5(2), 43–56 (1998)
Kunda, M., McGreggor, K., Goel, A.: Taking a Look (Literally!) at the Raven’s Intelligence Test: Two Visual Solution Strategies. In: Proc. 32nd Annual Meeting of the Cognitive Science Society, Portland (August 2010)
Kunda, M., McGreggor, K., Goel, A.: A computational model for solving problems from the Raven’s Progressive Matrices intelligence test using iconic visual representations. To appear in Cognitive Systems Research (in press)
Lovett, A., Lockwood, K., Forbus, K.: Modeling Cross-Cultural Performance on the Visual Oddity Task. In: Freksa, C., Newcombe, N.S., Gärdenfors, P., Wölfl, S. (eds.) Spatial Cognition VI. LNCS (LNAI), vol. 5248, pp. 378–393. Springer, Heidelberg (2008)
Mandelbrot, B.: The fractal geometry of nature. W.H. Freeman, San Francisco (1982)
Markou, M., Singh, S.: Novelty Detection: A Review-Part 1: Statistical Approaches. Signal Processing 83(12), 2481–2497 (2003a)
Markou, M., Singh, S.: Novelty Detection: A Review-Part 2: Neural Network Based Approaches. Signal Processing 83(12), 2481–2497 (2003b)
McGreggor, K., Kunda, M., Goel, A.: Fractal Analogies: Preliminary Results from the Raven’s Test of Intelligence. In: Proc. International Conference on Computational Creativity, Mexico City, Mexico, April 27-29 (2011)
Norman, D.: Cognition in the Head and in the World: An Introduction to the Special Issue on Situated Action. Cognitive Science 17, 1–6 (1993)
Neto, H., Nehmzow, U.: Visual Novelty Detection with Automatic Scale Selection. Robotics and Autonomous Systems 55, 693–701 (2007)
O’Reilly, R.C., Johnson, M.H.: Object Recognition and Sensitive Periods: A Computational Analysis of Visual Imprinting. Neural Computation 6, 357–389 (1994)
Reynolds, C. W.: Flocks, Herds, and Schools: A Distributed Behavioral Model. Computer Graphics 21(4), 25–34 (1987) (SIGGRAPH 1987 Conference Proceedings)
Reynolds, C.W.: Steering Behaviors For Autonomous Characters. In: Proceedings of Game Developers Conference 1999 held in San Jose, California, pp. 763–782. Miller Freeman Game Group, San Francisco (1999)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice-Hall (2003)
Tversky, A.: Features of similarity. Psychological Review 84(4), 327–352 (1977)
Wagemans, J., Elder, J., Kubovy, M., Palmer, S., Peterson, M., Singh, M., von der Heydt, R.: A century of Gestalt psychology in visual perception: I. Perceptual grouping and figure-ground organization. Psychological Bulletin (in press A)
Wagemans, J., Feldman, J., Gerpshtein, S., Kimchi, R., Pomerantz, J., van der Helm, P., van Leeuwen: A Century of Gestalt Psychology in Visual Perception II. Conceptual and Theoretical Foundations. Psychological Bulletin (in press B)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
McGreggor, K., Goel, A. (2012). Fractal Analogies for General Intelligence. In: Bach, J., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2012. Lecture Notes in Computer Science(), vol 7716. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35506-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-35506-6_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35505-9
Online ISBN: 978-3-642-35506-6
eBook Packages: Computer ScienceComputer Science (R0)