Weight Adaptation Stability of Static Quadratic Neural Unit
Result description
This paper is focused on weight adaptation stability analysis of static quadratic neural unit (QNU) which is considered a high nonlinear approximator. The aim of this paper is to provide verifiable conditions in which the weight system of QNU is stable during real time adaptation. The paper presents a novel approach toward stability of static QNU before we focus on stability of the dynamic type of QNU.
Keywords
static quadratic neural unitstabilityweight systemmatrix of dynamicseigenvalues
The result's identifiers
Result code in IS VaVaI
Result on the web
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Weight Adaptation Stability of Static Quadratic Neural Unit
Original language description
This paper is focused on weight adaptation stability analysis of static quadratic neural unit (QNU) which is considered a high nonlinear approximator. The aim of this paper is to provide verifiable conditions in which the weight system of QNU is stable during real time adaptation. The paper presents a novel approach toward stability of static QNU before we focus on stability of the dynamic type of QNU.
Czech name
—
Czech description
—
Classification
Type
O - Miscellaneous
CEP classification
JB - Sensors, detecting elements, measurement and regulation
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Basic information
Result type
O - Miscellaneous
CEP
JB - Sensors, detecting elements, measurement and regulation
Year of implementation
2011