Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Jau-Chi Huang"'
Publikováno v:
Knowledge-Based Systems
We report the discovery of strong correlations between protein coding regions and the prediction errors when using the simple recurrent network to segment genome sequences. We are going to use SARS genome to demonstrate how we conduct training and de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2bbbd67605eadec9cd6acaacc86cfd49
https://doi.org/10.1016/j.knosys.2011.09.001
https://doi.org/10.1016/j.knosys.2011.09.001
Publikováno v:
Neurocomputing. 71:3140-3149
This paper presents a new mapping to construct the self-organizing map on the curved seamless surface. This mapping is developed for the planar triangle surface derived from the conformal self-organizing map [C.-Y. Liou, Y.-T. Kuo, Conformal self-org
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::346af46f689d32e362df36afabbf82fa
https://doi.org/10.1016/j.neucom.2008.04.031
https://doi.org/10.1016/j.neucom.2008.04.031
Publikováno v:
Neurocomputing. 71:3150-3157
This paper presents an automatic acquisition process to acquire the semantic meaning for the words. This process obtains the representation vectors for stemmed words by iteratively improving the vectors, using a trained Elman network. Experiments per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::713e0ed3443025c26349f688cd1051b5
https://doi.org/10.1016/j.neucom.2008.04.030
https://doi.org/10.1016/j.neucom.2008.04.030
Autor:
Jau-Chi Huang, 黃昭綺
99
Elman network can discover the hidden structure of sequential data. This thesis uses Elman network to process the genome sequence and detects the boundary of the protein coding region according to the prediction error. Moreover, for literal w
Elman network can discover the hidden structure of sequential data. This thesis uses Elman network to process the genome sequence and detects the boundary of the protein coding region according to the prediction error. Moreover, for literal w
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/49489218632258871735
Publikováno v:
Intelligent Information and Database Systems ISBN: 9783642200380
ACIIDS (1)
ACIIDS (1)
We present a novel method to train the Elman network to learn literal works. This paper reports findings and results during the training process. Both codes and network weights are trained by using this method. The training error can be greatly reduc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23576b97eafd7464806c13594b52069c
https://doi.org/10.1007/978-3-642-20039-7_17
https://doi.org/10.1007/978-3-642-20039-7_17
Autor:
Cheng-Yuan Liou, Jau-Chi Huang
Publikováno v:
Artificial Neural Networks – ICANN 2010 ISBN: 9783642158247
ICANN (3)
ICANN (3)
Any point in the solution space of a perceptron can classify the training data correctly. Two kinds of the solution space, one in the weight space and the other in the input space, have been devised. This work illustrated the correspondence between t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f77e62286ba60553fdd161aec16e060
https://doi.org/10.1007/978-3-642-15825-4_34
https://doi.org/10.1007/978-3-642-15825-4_34
Autor:
King, Irwin, Jun Wang, Laiwan Chan, DeLiang Wang, Cheng-Yuan Liou, Yen-Ting Kuo, Jau-Chi Huang
Publikováno v:
Neural Information Processing; 2006, p1012-1021, 10p
Autor:
King, Irwin, Jun Wang, Laiwan Chan, DeLiang Wang, Cheng-Yuan Liou, Jau-Chi Huang, Wen-Chie Yang
Publikováno v:
Neural Information Processing; 2006, p183-192, 10p
Publikováno v:
Neural Information Processing ISBN: 9783540464792
ICONIP (1)
ICONIP (1)
This paper presents a method to construct a smooth seamless conformal surface for the genus-0 manifold. The method is developed for the conformal self-organizing map [10]. The constructed surface is both piecewise smooth and continuous. The mapping b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abfefa8a981fc2a52adfcc204361645c
https://doi.org/10.1007/11893028_113
https://doi.org/10.1007/11893028_113
Publikováno v:
Neural Information Processing ISBN: 9783540464792
ICONIP (1)
ICONIP (1)
This paper presents an automatic acquisition process to acquire the semantic meaning for the words. This process obtains the representation vectors for stemmed words by iteratively improving the vectors, using a trained Elman network [4]. Experiments
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6198cbbb165ec8afdf0845bee89725f8
https://doi.org/10.1007/11893028_21
https://doi.org/10.1007/11893028_21