Complexity of perceptron recognition for a class of geometric patterns
Abstract
In this paper, we study the recognition complexity of discrete geometric figures (rectangles, squares, circles, ellipses) on a retina by diameter-limited and order-restricted perceptrons. We construct a diameter-limited recognition perceptron for the family of rectangles, beginning with local configurations, which is different from the one shown by Minsky et al. (Perceptrons: An Introduction to Computational Geometry, extended edition, MIT Press, Cambridge, MA, 1988). In addition, we demonstrate the nonexistence of diameter-limited recognition perceptrons for squares, circles and ellipses. Finally, for squares and ellipses we construct an order-restricted perceptron with constant coefficients, using an original technique which decomposes the characterization of the figures into local and global features. © 2002 Elsevier Science B.V. All rights reserved.
Más información
Título según WOS: | Complexity of perceptron recognition for a class of geometric patterns |
Título según SCOPUS: | Complexity of perceptron recognition for a class of geometric patterns |
Título de la Revista: | THEORETICAL COMPUTER SCIENCE |
Volumen: | 299 |
Número: | 01-mar |
Editorial: | Elsevier |
Fecha de publicación: | 2003 |
Página de inicio: | 65 |
Página final: | 79 |
Idioma: | English |
URL: | http://linkinghub.elsevier.com/retrieve/pii/S0304397501002663 |
DOI: |
10.1016/S0304-3975(01)00266-3 |
Notas: | ISI, SCOPUS |