Accession Number : AD0731304

Title :   Pattern Recognition Properties of Multilinear Machines,

Corporate Author : STANFORD UNIV CALIF DEPT OF OPERATIONS RESEARCH

Personal Author(s) : Kalman,R. E.

Report Date : SEP 1968

Pagination or Media Count : 41

Abstract : It is well known that pattern-recognition linear machine properties of a (finite-dimensional linear dynamical system) may be identified with the input/state map (polynomials) map to (polynomials mod characteristic polynomial). In a similar way, the pattern-recognition action of a multilinear machine is describable by projections into certain complicated equivalence classes constructed on the input space. The results reported here, obtained very recently, give a firm mathematical foundation to earlier attempts by Norbert Wiener and many others to analyze nonlinear system problems using generalized Volterra kernels and Hermite expansions. (Author)

Descriptors :   (*ALGEBRA, SYSTEMS ENGINEERING), (*PATTERN RECOGNITION, MATHEMATICAL ANALYSIS), SET THEORY, LINEAR SYSTEMS, POLYNOMIALS, SEQUENCES, TRANSFER FUNCTIONS, VECTOR SPACES

Subject Categories : Theoretical Mathematics
      Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE