An Approach to Stable Gradient Descent Adaptation of Higher-Order Neural Units
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F17%3A00242907" target="_blank" >RIV/68407700:21220/17:00242907 - isvavai.cz</a>
Result on the web
<a href="http://ieeexplore.ieee.org/document/7487017/" target="_blank" >http://ieeexplore.ieee.org/document/7487017/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TNNLS.2016.2572310" target="_blank" >10.1109/TNNLS.2016.2572310</a>
Alternative languages
Result language
angličtina
Original language name
An Approach to Stable Gradient Descent Adaptation of Higher-Order Neural Units
Original language description
Stability evaluation of a weight-update system of higher-order neural units (HONUs) with polynomial aggregation of neural inputs (also known as classes of polynomial neural networks) for adaptation of both feedforward and recurrent HONUs by a gradient descent method is introduced. An essential core of the approach is based on spectral radius of a weight-update system, and it allows stability monitoring and its maintenance at every adaptation step individually. Assuring stability of the weight-update system (at every single adaptation step) naturally results in adaptation stability of the whole neural architecture that adapts to target data. As an aside, the used approach highlights the fact that the weight optimization of HONU is a linear problem, so the proposed approach can be generally extended to any neural architecture that is linear in its adaptable parameters
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
20301 - Mechanical engineering
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
IEEE Transactions on Neural Networks and Learning Systems
ISSN
2162-237X
e-ISSN
2162-2388
Volume of the periodical
28
Issue of the periodical within the volume
9
Country of publishing house
US - UNITED STATES
Number of pages
13
Pages from-to
2022-2034
UT code for WoS article
000407761500005
EID of the result in the Scopus database
2-s2.0-84973527093