System Modeling and Statistical Data Processing.
Abstract
The report discusses research in two related areas. The first area is focused on certain system identification problems, e.g., (1) structural properties of realizations of discrete-time Markovian processes, (2) a reproducing kernel Hilbert space approach to spline problems with applications in estimation and control, and (3) deterministic realization problems of obtaining minimal state-variable and transfer function realizations of impulse-response matrices. The second area is focused on broadcast channels and information theory, learning with finite memory, and nonparametric pattern recognition, e.g., (1) the effects of randomization in hypothesis testing experiment programs on use of the finite memory capacity of a digital computer, (2) compound Bayes decision problems, (3) determination of the rationality of the mean of a random variable, (4) data compression by enumeration of sequences, and (5) complexity approaches to statistical data processing. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 20, 1972
- Accession Number
- AD0746070
Entities
People
- Thomas Kailath
- Thomas M. Cover
Organizations
- Stanford University