|
|
Gaussian Processes Based Hyper-Optimization of Neural Networks
Coufal, Martin ; Landini, Federico Nicolás (oponent) ; Beneš, Karel (vedoucí práce)
The goal of this thesis is to create a lightweight toolkit for artificial neural network hyper-parameter optimisation. The optimisation toolkit has to be able to optimise multiple, possibly correlated hyper-parameters. I solved this problem by creating an optimiser that uses Gaussian processes to predict the influence of the hyper-parameters on the resulting neural network accuracy. Based on the experiments on multiple benchmark functions, the toolkit is able to provide better results than random search optimisation and thus reduce the number of necessary optimisation steps. The random search optimisation provided better results only in the first few optimisation steps before Gaussian process optimisation creates sufficient model of the problem. However the experiments on MNIST dataset show that random optimisation achieves almost always better results than used GP optimiser. These differences between the experiments results are probably caused by insufficient complexity of the benchmarks or by selected parameters of the implemented optimiser.
|
|
|
Narrative in Computer Games
Musilová, Monika ; Walek, Agata (oponent) ; Ellederová, Eva (vedoucí práce)
This Bachelor’s thesis deals with an issue of a narrative in computer games. In the introductory chapters, general games specifications, such as rules and genres of the games, are formulated. The main focus is then on linear and interactive forms of the narrative and on the means they are most frequently represented by. The practical part of the thesis is devoted to the analysis of two selected games, focusing on the narrative means used and on the way they influence the game’s linearity and interactivity. For each game, a storyline scheme is created on whose basis a narrative structure of the game is determined.
|
|
|
Gaussian Processes Based Hyper-Optimization of Neural Networks
Coufal, Martin ; Landini, Federico Nicolás (oponent) ; Beneš, Karel (vedoucí práce)
The goal of this thesis is to create a lightweight toolkit for artificial neural network hyper-parameter optimisation. The optimisation toolkit has to be able to optimise multiple, possibly correlated hyper-parameters. I solved this problem by creating an optimiser that uses Gaussian processes to predict the influence of the hyper-parameters on the resulting neural network accuracy. Based on the experiments on multiple benchmark functions, the toolkit is able to provide better results than random search optimisation and thus reduce the number of necessary optimisation steps. The random search optimisation provided better results only in the first few optimisation steps before Gaussian process optimisation creates sufficient model of the problem. However the experiments on MNIST dataset show that random optimisation achieves almost always better results than used GP optimiser. These differences between the experiments results are probably caused by insufficient complexity of the benchmarks or by selected parameters of the implemented optimiser.
|
|
|
Narrative in Computer Games
Musilová, Monika ; Walek, Agata (oponent) ; Ellederová, Eva (vedoucí práce)
This Bachelor’s thesis deals with an issue of a narrative in computer games. In the introductory chapters, general games specifications, such as rules and genres of the games, are formulated. The main focus is then on linear and interactive forms of the narrative and on the means they are most frequently represented by. The practical part of the thesis is devoted to the analysis of two selected games, focusing on the narrative means used and on the way they influence the game’s linearity and interactivity. For each game, a storyline scheme is created on whose basis a narrative structure of the game is determined.
|
host ::
RSS.