Národní úložiště šedé literatury Nalezeno 2 záznamů.  Hledání trvalo 0.01 vteřin. 
Parallel optimization methods
Marcina, Tomáš ; Kozovský, Matúš (oponent) ; Kozubík, Michal (vedoucí práce)
The work is concerned on the comparison of different algorithms designed for the optimization of multidimensional functions. Specifically, it deals with population optimization methods, which are generally suitable for parallelizing the calculation of the optimal function value. The functions are implemented in program Matlab and on the NVIDIA CUDA platform. It compares several different algorithms suitable for this. At the end, the advantages and disadvantages of individual algorithms are summarized.
Optimization of Multilayer Perceptron Training Parameters Using Artificial Bee Colony and Genetic Algorithm
Kartci, A.
In this paper, the momentum coefficient, learning rate, and the number of hidden neurons where the multilayer perceptron works best, are determined. The network and optimization algorithms are written in MATLAB, which was also successfully used to carry out results. To obtain the results, IRIS, mammographic_mass, and new_thyroid data sets have been used. Obtained results show that the determining effect on the neural learning process of parameters (momentum coefficient, learning rate, number of hidden neurons) are compatible with other approaches available in the literature. Both genetic algorithm (GA) and artificial bee colony (ABC) algorithm were successful on finding the values to get high performance as well as effect on performance of the population number.

Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.