Zobrazeno 1 - 10
of 54
pro vyhledávání: '"H. A. Ceccatto"'
Publikováno v:
IEEE Transactions on Neural Networks. 22:37-51
Many learning problems may vary slowly over time: in particular, some critical real-world applications. When facing this problem, it is desirable that the learning method could find the correct input-output function and also detect the change in the
Publikováno v:
Neurocomputing. 70:2363-2370
We present a general strategy for filling the missing data of the CATS benchmark time series prediction competition. Our approach builds upon a time-symmetric embedding of this time series and the use of a one-shot forecasting for each missing value
Publikováno v:
Computers and Electronics in Agriculture. 47:15-24
We explore the feasibility of implementing fast and reliable computer-based systems for the automatic identification of weed seeds from color and black and white images. Seeds size, shape, color and texture characteristics are obtained by standard im
Publikováno v:
Solar Physics. 221:167-177
The sunspot record of solar magnetic activity is studied as a nonstationary time series by means of a previously developed algorithm for treating perturbed dynamical systems. This approach incorporates secular changes into the modeling process throug
Publikováno v:
Computers and Electronics in Agriculture. 33:91-103
The implementation of new methods for reliable and fast identification and classification of seeds is of major technical and economical importance in the agricultural industry. As in ocular inspection, the automatic classification of seeds should be
Autor:
L O Manuel, H A Ceccatto
Publikováno v:
Canadian Journal of Physics. 79:1543-1549
We study, within the Schwinger-boson approach, the ground-state structure of two Heisenberg anti-ferromagnets on the triangular lattice: the J1 J2 model, which includes a next-nearest-neighbor coupling J2, and the spatially-anisotropic J1 J'1 m
Publikováno v:
International Journal of Neural Systems. 11:305-310
Ensembles of artificial neural networks have been used in the last years as classification/regression machines, showing improved generalization capabilities that outperform those of single networks. However, it has been recognized that for aggregatio
Autor:
H. A. Ceccatto, Rafael A. Calvo
Publikováno v:
Intelligent Data Analysis. 4:411-420
In this work we investigate some technical questions related to the application of neural networks in document classification. First, we discuss the effects of different averaging protocols for the \chi ^{2} statistic used to remove non-informative t
Publikováno v:
Physical Review B. 62:6991-6996
We consider a modified extended Hubbard model (EHM) which, in addition to the on-site repulsion U and nearest-neighbor repulsion V, includes polarization effects in second-order perturbation theory. The model is equivalent to an EHM with renormalized
Autor:
H. A. Ceccatto, Luis O. Manuel
Publikováno v:
Physical Review B. 61:3470-3474
We study the stability of homogeneous magnetic phases in a generalized t-J model including a same-sublattice hopping t' and nearest-neighbor repulsion V by means of the slave fermion-Schwinger boson representation of spin operators. At mean-field ord