Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Jorge Sueiras"'
Publikováno v:
Neurocomputing. 289:119-128
This paper proposes the use of a new neural network architecture that combines a deep convolutional neural network with an encoder–decoder, called sequence to sequence, to solve the problem of recognizing isolated handwritten words. The proposed ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1160fad7f9d1690f1cb0f7e72583bcdd
https://doi.org/10.1016/j.neucom.2018.02.008
https://doi.org/10.1016/j.neucom.2018.02.008
Publikováno v:
Statistical Methods & Applications. 25:477-499
In this paper, a methodology is proposed in order to produce a set of seeds later used as a starting point to K-Means-type unsupervised classification algorithms for text mining. Our proposal involves using the eigenvectors obtained from principal co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::571470b9612540b1e50c22a4c910df8e
https://doi.org/10.1007/s10260-015-0345-4
https://doi.org/10.1007/s10260-015-0345-4
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783319534794
ISDA
ISDA
We present our current work on building a deep learning architecture for the offline handwritten character recognition problem. The proposed system is based on training a deep Convolutional Neural Network (CNN) to recognize handwritten characters, us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::094aadb99e8ce9b8a3bff76b78297372
https://doi.org/10.1007/978-3-319-53480-0_30
https://doi.org/10.1007/978-3-319-53480-0_30
Autor:
Ángel Sánchez, José Francisco Vélez, Jorge Sueiras, Maria Teresa Gonzalez de Lena, Victoria Ruíz
Publikováno v:
Biomedical Applications Based on Natural and Artificial Computing ISBN: 9783319597720
IWINAC (2)
IWINAC (2)
Nowadays, Deep Learning is one of the most popular techniques which is used in several fields like handwriting text recognition. This paper presents our propose for a handwritten digit sequences recognition system. Our system, based in two stage mode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4479345a78d98a2d4f29f53f3595203
https://doi.org/10.1007/978-3-319-59773-7_20
https://doi.org/10.1007/978-3-319-59773-7_20
Publikováno v:
ACM SIGKDD Explorations Newsletter. 9:70-74
This paper presents a solution to the KDD CUP 2007 task "How Many Ratings?". The combination of three different approaches is used to produce a final solution which improves the results obtained by each of these procedures by itself.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a2a4b80e3c016ecf2f5873bbc9c4c1a
https://doi.org/10.1145/1345448.1345464
https://doi.org/10.1145/1345448.1345464
Publikováno v:
ACM SIGKDD Explorations Newsletter. 9:57-61
This paper describes one possible way to solve task "Who rated what?" of the KDD CUP 2007. The proposed solution is a history-based model that predicts whether a user will vote a given movie. Key points to our approach are (1) the estimation of the m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b85a04aa71925cf2fa13dc33cd619bc3
https://doi.org/10.1145/1345448.1345461
https://doi.org/10.1145/1345448.1345461
Publikováno v:
Proceedings of the 1st international workshop on Data mining and audience intelligence for advertising.
The advance of the Internet as a competitor with traditional media (radio, TV, newspapers and magazines) is attracting advertisements, but traditional analytical tools for media planning are not directly applicable. In this paper we describe our expe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ed416427a316aae9acdbfbbc118ad2a
https://doi.org/10.1145/1348599.1348609
https://doi.org/10.1145/1348599.1348609