An Approach to Stable Gradient Descent Adaptation of Higher-Order Neural Units

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

An Approach to Stable Gradient Descent Adaptation of Higher-Order Neural Units

Popis výsledku v původním jazyce

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

Název v anglickém jazyce

An Approach to Stable Gradient Descent Adaptation of Higher-Order Neural Units

Popis výsledku anglicky

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

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20301 - Mechanical engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Neural Networks and Learning Systems

ISSN

2162-237X

e-ISSN

2162-2388

Svazek periodika

28

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

13

Strana od-do

2022-2034

Kód UT WoS článku

000407761500005

EID výsledku v databázi Scopus

2-s2.0-84973527093