| bibtype |
J -
Journal Article
|
| ARLID |
0108848 |
| utime |
20240103173347.2 |
| mtime |
20050419235959.9 |
| WOS |
000225681000006 |
| SCOPUS |
8744285897 |
| DOI |
10.1016/j.neucom.2003.12.005 |
| title
(primary) (eng) |
Robust RBF Finite Automata |
| specification |
|
| serial |
| ARLID |
cav_un_epca*0257314 |
| ISSN |
0925-2312 |
| title
|
Neurocomputing |
| volume_id |
62 |
| page_num |
93-110 |
| publisher |
|
|
| title
(cze) |
Robustní RBF konečné automaty |
| keyword |
radial basis function |
| keyword |
neural network |
| keyword |
finite automaton |
| keyword |
Boolean circuit |
| keyword |
computational power |
| author
(primary) |
| ARLID |
cav_un_auth*0108377 |
| name1 |
Šorel |
| name2 |
Michal |
| institution |
UTIA-B |
| full_dept |
Department of Image Processing |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0100836 |
| name1 |
Šíma |
| name2 |
Jiří |
| institution |
UIVT-O |
| full_dept |
Department of Theoretical Computer Science |
| fullinstit |
Ústav informatiky AV ČR, v. v. i. |
|
| COSATI |
12 |
| cas_special |
| project |
| project_id |
IAB2030007 |
| agency |
GA AV ČR |
| ARLID |
cav_un_auth*0013875 |
|
| project |
| project_id |
LN00A056 |
| agency |
GA MŠk |
| ARLID |
cav_un_auth*0027911 |
|
| abstract
(eng) |
The computational power of recurrent RBF(radial basis functions) networks is investigated.A recurrent network which consists of O(sqrt(m logm)) RBF units with maximum norm employing any activation function that has different values in at least two nonnegative points,is constructed so as to implement a given deterministic finite automaton with m states.The underlying simulation proves to be robust with regard to analog noise for a large class of smooth activation functions with a special type of inflections. |
| abstract
(cze) |
Zkoumáme vypočetni sílu rekurentních RBF (radiálních bazických funkcí) sítí. Zkonstruujeme rekurentní síť s O(sqrt(m log m)) RBF jednotkami s kubickou normou a aktivační funkci nabývající různých hodnot alespoň ve dvou nezáporných bodech, která implementuje deterministický konečný automat s m stavy. Dokážeme, ze pro velkou třídu hladkých aktivačních funkci se speciálním typem inflexe je příslušná simulace robustní vůči omezenému analogovému šumu. |
| reportyear |
2005 |
| RIV |
BA |
| mrcbC52 |
4 O 4o 20231122133042.8 |
| permalink |
http://hdl.handle.net/11104/0015963 |
| ID_orig |
UIVT-O 20040258 |
| arlyear |
2004 |
| mrcbTft |
\nSoubory v repozitáři: 0108848.pdf |
| mrcbU14 |
8744285897 SCOPUS |
| mrcbU34 |
000225681000006 WOS |
| mrcbU63 |
cav_un_epca*0257314 Neurocomputing 0925-2312 1872-8286 Roč. 62 - 2004 93 110 Elsevier |
|