Buscar
Mostrando ítems 41-50 de 534
UNSUPERVISED LAND-COVER CLASSIFICATION THROUGH HYPER-HEURISTIC-BASED HARMONY SEARCH
(Ieee, 2015-01-01)
Unsupervised land-cover classification aims at learning intrinsic properties of spectral and spatial features for the task of area coverage in urban and rural areas. In this paper, we propose to model the problem of ...
Model selection for discriminative restricted boltzmann machines through meta-heuristic techniques
(2015)
Discriminative learning of Restricted Boltzmann Machines has been recently introduced as an alternative to provide a self-contained approach for both unsupervised feature learning and classification purposes. However, one ...
Modelos e algoritmos para a otimização do planejamento da produção de grãos eletrofundidos
(Universidade Federal de São CarlosBRUFSCarPrograma de Pós-Graduação em Engenharia de Produção - PPGEP, 2011-02-12)
The number of successful applications that use optimization models has followed the evolution of the computers, as much in hardware, with more powerful machines, as in software, with more intelligent algorithms. Due to ...
Genetic local search for multi-objective flowshop scheduling problems
(Elsevier Science BvAmsterdamHolanda, 2005)
Evolutionary Algorithm for the Vehicles Routing Problem with Time Windows Based on a Constraint Satisfaction Technique
(Revista Computación y Sistemas; Vol. 13 No.3, 2010-02-18)
Abstract. In this paper a Memetic Algorithm (MA) is proposed for solving the Vehicles Routing Problem with Time Win-dows (VRPTW) multi-objective, using a constraint satisfaction heuristic that allows pruning of the search ...
Fine-Tuning Dropout Regularization in Energy-Based Deep Learning
(2021-01-01)
Deep Learning architectures have been extensively studied in the last years, mainly due to their discriminative power in Computer Vision. However, one problem related to such models concerns their number of parameters and ...
A new algorithm for time series prediction using machine learning models
Two stage grid search accepted as a promising heuristic search technique, involves a search performed in two stages. In the first stage a search is performed in coarse grain/low resolution to identify the optimal region ...
An Effective Inverse Heat Transfer Procedure Based On Evolutionary Algorithms To Determine Cooling Conditions Of A Steel Continuous Casting Machine
(TAYLOR & FRANCIS INCPHILADELPHIA, 2015)