Zobrazeno 1 - 10
of 296
pro vyhledávání: '"Oja, E"'
Autor:
Oja, E. (Erik)
The United States began pursuing a transition to majority rule in Rhodesia in 1976 by Secretary of State Henry Kissinger. Kissinger had noted the situation in Rhodesia already in 1969 but chose to pursue majority rule in order to de-escalate the arme
Externí odkaz:
http://urn.fi/URN:NBN:fi:oulu-201706012325
Publikováno v:
In Journal of Mathematical Analysis and Applications 2009 354(1):159-164
Publikováno v:
Lecture Notes in Computer Science ; 2714, 562-569. Berlin : Springer
STARTPAGE=562;ENDPAGE=569;TITLE=Lecture Notes in Computer Science ; 2714
Kaynak, O.; Alpaydin, E.; Oja, E. (ed.), Artificial Neural Networks and Neural Information Processing-Ican/Iconip 2003, pp. 562-569
Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 ISBN: 9783540404088
ICANN
STARTPAGE=562;ENDPAGE=569;TITLE=Lecture Notes in Computer Science ; 2714
Kaynak, O.; Alpaydin, E.; Oja, E. (ed.), Artificial Neural Networks and Neural Information Processing-Ican/Iconip 2003, pp. 562-569
Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003 ISBN: 9783540404088
ICANN
Switching linear dynamic systems can monitor systems that operate in different regimes. In this article we introduce a class of multi-scale switching linear dynamical systems that are particularly suited if such regimes form a hierarchy. The setup co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eea54a470546d26e547284d994be96ef
http://hdl.handle.net/2066/100948
http://hdl.handle.net/2066/100948
Autor:
Heskes, T.M., Oja, E.
Publikováno v:
Oja, E. (ed.), Kohonen Maps, pp. 303-315
Oja, E. (ed.), Kohonen Maps, 303-315. Amsterdam : Elsevier
STARTPAGE=303;ENDPAGE=315;TITLE=Oja, E. (ed.), Kohonen Maps
Oja, E. (ed.), Kohonen Maps, 303-315. Amsterdam : Elsevier
STARTPAGE=303;ENDPAGE=315;TITLE=Oja, E. (ed.), Kohonen Maps
Publisher Summary By changing the definition of the winning unit, Kohonen's original learning rule can be viewed as performing stochastic gradient descent on an energy function. It is showed in two ways: by explicitly computing derivatives and as a l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b9cec99350907512648543d61d1032ae
https://hdl.handle.net/2066/100971
https://hdl.handle.net/2066/100971
Publikováno v:
Artificial Neural Networks: Biological Inspirations – ICANN 2005 ISBN: 9783540287520
ICANN (1)
Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005, 525-530
STARTPAGE=525;ENDPAGE=530;TITLE=Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005
ICANN (1)
Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005, 525-530
STARTPAGE=525;ENDPAGE=530;TITLE=Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005
In this paper we apply cellular neural networks for color image segmentation. Color aerial photographs will be analyzed. Two types of color models: RGB and HSV will be taken into account and compared. In resulting images we will distinguish some obje
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1e538cdb52c0b7d1194e3ff875bb908
https://doi.org/10.1007/11550822_82
https://doi.org/10.1007/11550822_82
Publikováno v:
EPRINTS-BOOK-TITLE
In this work, we describe a character recognition system we have implemented for experimenting with selfsupervised adaptation method. The Dynamic Time Warping algorithm is used for matching input characters to prototypes and recognition is carried
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::b64a989b1d982db1dc2e77011d74e356
https://research.rug.nl/en/publications/0bd2e2a4-f1e3-437b-9eef-fd9bc5ecd2c3
https://research.rug.nl/en/publications/0bd2e2a4-f1e3-437b-9eef-fd9bc5ecd2c3
Publikováno v:
ARTIFICIAL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING-ICAN/ICONIP 2003, 846-853
STARTPAGE=846;ENDPAGE=853;TITLE=ARTIFICIAL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING-ICAN/ICONIP 2003
STARTPAGE=846;ENDPAGE=853;TITLE=ARTIFICIAL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING-ICAN/ICONIP 2003
We propose a simple method to map a generic threshold model, namely the Spike Response Model, to artificial data of neuronal activity using a minimal amount of a priori information. Here, data are generated by a detailed mathematical model of neurona
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::338d28a65c440eb0517481e273b1dbc4
https://cris.maastrichtuniversity.nl/en/publications/6b9e5aa6-9d2a-46f7-9c87-b5ad8598123e
https://cris.maastrichtuniversity.nl/en/publications/6b9e5aa6-9d2a-46f7-9c87-b5ad8598123e
Publikováno v:
Proceedings of the International Conference of the Artificial Neural Networks and Neural Information Processing, 82-85
STARTPAGE=82;ENDPAGE=85;TITLE=Proceedings of the International Conference of the Artificial Neural Networks and Neural Information Processing
STARTPAGE=82;ENDPAGE=85;TITLE=Proceedings of the International Conference of the Artificial Neural Networks and Neural Information Processing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::7158fef10f204a53f2f96cd13653377b
https://pure.eur.nl/en/publications/06b9398f-3688-46d7-a18e-9465e4167ef4
https://pure.eur.nl/en/publications/06b9398f-3688-46d7-a18e-9465e4167ef4