Accession Number:

ADA336426

Title:

Topics in Stochastics, Symbolic Dynamics and Neural Networks

Descriptive Note:

Final rept. 1 Jun 93-31 Dec 96

Corporate Author:

OREGON STATE UNIV CORVALLIS DEPT OF MATHEMATICS

Personal Author(s):

Report Date:

1996-12-31

Pagination or Media Count:

3.0

Abstract:

Research was supported in inverse application areas of probability, ergodic theory and dynamical systems including neural networks. Theorems on rates of learning in unsupervised Neural Networks, relating to the sampling method for available environmental data were obtained. Results on the consistency and effectiveness of estimators for correlation dimension were derived, together with advanced percolation structures useful in mammalian lung development models. Ways of using continued fractions to construct highly mixing stochastic processes were expounded.

Subject Categories:

  • Statistics and Probability
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE