Learning of recognizable picture languages
Learning of certain classes of two-dimensional picture languages is considered. Linear time algorithms that learn in the limit, from positive data the classes of local picture languages and locally testable picture languages are presented. A crucial step for obtaining the learning algorithm for local picture languages is an explicit construction of a two-dimensional on-line tessellation acceptor for a given local picture language. An efficient algorithm that learns the class of recognizable picture languages from positve data and restricted subset queries, is presented in contrast to the fact that this class is not learnable in the limit from positive data alone.
Unable to display preview. Download preview PDF.
- 1.D. Angluin, Inductive inference of formal languages from positive data, Information and control 45:117–135, 1980.Google Scholar
- 2.D. Giammarressi and A. Restivo, Recognizable picure languages, Proc. of the International Colloquium on Parallel Image Processing (Eds. M. Nivat, A. Saoudi and P.S.P. Wang), Paris (1991), 3–16.Google Scholar
- 3.K. Inoue and I. Takanami, A characterization of recogniable picture languages, Tech. Report, Yamaguchi University, Ube, Japan, 1991.Google Scholar
- 4.R. Siromoney, Array Languages and Lindenmayer systems — a survey in the Book of L, eds. G. Rozenberg and A. Salomaa, Springer-Verlag, Berlin, 1985.Google Scholar
- 5.R. Siromoney, K.G. Subramanian and Lisa Mathew, Learning of Pattern and picture languages, Proc. of the International Colloquium on Parallel Image Processing (Eds. M. Nivat, A. Saoudi and P.S.P. Wang), Paris (1991).Google Scholar
- 6.L. Pitt, Inductive inference, DFAs and computational complexity, in Analogical and Inductive Inference, Lecture notes in Artificial Intelligence 397, Springer Verlag, 1989, 18–44.Google Scholar
- 7.Yokomori, Learning local languages from positive data, in Proc. Fujitsu IIAS — SIS Workshop on Computational Learning Theory '89, Numazu (1989).Google Scholar