|
|
Object Recognition by Neural Networks
Marák, Jaroslav ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This thesis is focused on neural networks and their classification capability in object recognition tasks. For recognition is there used neural networks with feedforward architecture which is learned by Back Propagation algorithm. We discusses about problems which appear while a choosing topology of network or using various lerning-significant parametters while a learning process. Achieved results are presented in experiments with estimation.
|
|
|
Methods and algorithms for face recognition
Soukup, Jiří ; Heriban, Pavel (referee) ; Šťastný, Jiří (advisor)
This work is describing basic methods of face recognition. The methods PCA, LDA, ICA, trace tranfsorm, elastic bunch graph map, genetic algorithm and neural network are described. In practical part, the PCA, PCA + RBF neural network and genetic algorithms are implemented. The RBF neural network is used in the way of clasificator and genetic algorithm is used for RBF NN training in one case and for selecting eigenvectors from PCA method in the other case. This method, PCA + GA, called EPCA, outperform other methods tested in this work on the ORL testing database.
|
|
|
Aerodynamic analysis of the glider flexible wing
Jurina, Marek ; Vaněk, František (referee) ; Navrátil, Jan (advisor)
This thesis deals with determination of effect of wing flexibility on load distribution. FSI analysis using modal superposition was used for determination of effect of wing flexibility. Analysis was verified by analytic calculation. Differences of load distribution, between rigid and flexible wing, was determined for the selected flight regimes. Change of the bending moment was up to 3,9 %. Thesis shows importance of including effect of wing flexibility for sailplane design.
|
|
|
Aerodynamic analysis of the glider flexible wing
Jurina, Marek ; Vaněk, František (referee) ; Navrátil, Jan (advisor)
This thesis deals with determination of effect of wing flexibility on load distribution. FSI analysis using modal superposition was used for determination of effect of wing flexibility. Analysis was verified by analytic calculation. Differences of load distribution, between rigid and flexible wing, was determined for the selected flight regimes. Change of the bending moment was up to 3,9 %. Thesis shows importance of including effect of wing flexibility for sailplane design.
|
|
|
Methods and algorithms for face recognition
Soukup, Jiří ; Heriban, Pavel (referee) ; Šťastný, Jiří (advisor)
This work is describing basic methods of face recognition. The methods PCA, LDA, ICA, trace tranfsorm, elastic bunch graph map, genetic algorithm and neural network are described. In practical part, the PCA, PCA + RBF neural network and genetic algorithms are implemented. The RBF neural network is used in the way of clasificator and genetic algorithm is used for RBF NN training in one case and for selecting eigenvectors from PCA method in the other case. This method, PCA + GA, called EPCA, outperform other methods tested in this work on the ORL testing database.
|
|
|
Object Recognition by Neural Networks
Marák, Jaroslav ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This thesis is focused on neural networks and their classification capability in object recognition tasks. For recognition is there used neural networks with feedforward architecture which is learned by Back Propagation algorithm. We discusses about problems which appear while a choosing topology of network or using various lerning-significant parametters while a learning process. Achieved results are presented in experiments with estimation.
|
guest ::
