Hadamard design and artificial neural nets

Hadamard theory is shown to play an important role in the generation of Boolean decision functions, a fundamental tool in the field of artificial neural network design. Based on a group-theoretic introduction of a complete set of Hadamard vectors, whose matrices are of the order of a power of two, t...

Full description

Saved in:
Bibliographic Details
Published in:Journal of statistical physics 1993-04, Vol.71 (1-2), p.327-339
Main Authors: KÜRTEN, K. E, KLINGEN, N
Format: Article
Language:English
Subjects:
DECISION MAKING
DESIGN
Exact sciences and technology
GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
GROUP THEORY
MATHEMATICS
MATRICES
NEURAL NETWORKS
Other topics in statistical physics, thermodynamics, and nonlinear dynamical systems
Physics
Statistical physics, thermodynamics, and nonlinear dynamical systems
TENSORS 990200 > Mathematics & Computers
TRANSFORMATIONS
VECTORS
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hadamard theory is shown to play an important role in the generation of Boolean decision functions, a fundamental tool in the field of artificial neural network design. Based on a group-theoretic introduction of a complete set of Hadamard vectors, whose matrices are of the order of a power of two, the authors classify subsets according to the degree of their linear dependence. They show in the thermodynamic limit that essentially the whole Hadamard space is occupied by representatives with defect not exceeding two or three. 15 refs., 1 fig.
ISSN:0022-4715
1572-9613
DOI:10.1007/BF01048103