Proceedings of the 14th Annual Conference of the Cognitive Science Society
Hillsdale, NJ: Erlbaum
Mental Imagery, Reconstructive Analogue, Memory
This paper proposes a new approach to mental imagery that has the potential for resolving an old debate. We show that the methods by which fractals emerge from dynamical systems provide a natural computational framework for the relationship between the “deep” representations of long-term visual memory and the “surface” representations of the visual array, a distinction which was proposed by (Kosslyn, 1980). The concept of an iterated function system (IFS) as a highly compressed representation for a complex topological set of points in a metric space (Barnsley, 1988) is embedded in a connectionist model for mental imagery tasks. Two advantages of this approach over previous models are the capability for topological transformations of the images, and the continuity of the deep representations with respect to the surface representations.
Stucki, David J. and Pollack, Jordan B., "Fractal (Reconstructive Analogue) Memory" (1992). Mathematics Faculty Scholarship. Paper 17.
Stucki, D. J. & Pollack, J. B. "Fractal (Reconstructive Analogue) Memory." Proceedings of the 14th Annual Conference of the Cognitive Science Society: (1992).