Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures With Gradient Learnings
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12310%2F21%3A43904125" target="_blank" >RIV/60076658:12310/21:43904125 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21220/23:00353615
Result on the web
<a href="https://doi.org/10.1109/TNNLS.2021.3123533" target="_blank" >https://doi.org/10.1109/TNNLS.2021.3123533</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TNNLS.2021.3123533" target="_blank" >10.1109/TNNLS.2021.3123533</a>
Alternative languages
Result language
angličtina
Original language name
Letter on Convergence of In-Parameter-Linear Nonlinear Neural Architectures With Gradient Learnings
Original language description
This letter summarizes and proves the concept of bounded-input bounded-state (BIBS) stability for weight convergence of a broad family of in-parameter-linear nonlinear neural architectures (IPLNAs) as it generally applies to a broad family of incremental gradient learning algorithms. A practical BIBS convergence condition results from the derived proofs for every individual learning point or batches for real-time applications.
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
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000826" target="_blank" >EF16_019/0000826: Center of Advanced Aerospace Technology</a><br>
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2021
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
Neuveden
Issue of the periodical within the volume
2021
Country of publishing house
US - UNITED STATES
Number of pages
4
Pages from-to
1-4
UT code for WoS article
000732275600001
EID of the result in the Scopus database
—