|
|
Increasing Reliability of Communication Networks
Hausner, Richard ; Komosný, Dan (referee) ; Koton, Jaroslav (advisor)
The bachelor's thesis deals with selected options for increasing reliability of communication networks. The basic protocols and network topologies are described in the thesis. In the second section the technologies of cascading, clustering and stacking network switches are discussed. The practical experiments and scenerios of connections, which are described in the aforementioned section, form a basis of their practical use proposal.
|
|
|
DRESS & GO: Deep belief networks and Rule Extraction Supported by Simple Genetic Optimization
Švaralová, Monika ; Mrázová, Iveta (advisor) ; Vomlelová, Marta (referee)
Recent developments in social media and web technologies offer new opportunities to access, analyze and process ever-increasing amounts of fashion-related data. In the appealing context of design and fashion, our main goal is to automatically suggest fashionable outfits based on the preferences extracted from real-world data provided either by individual users or gathered from the internet. In our case, the clothing items have the form of 2D-images. Especially for visual data processing tasks, recent models of deep neural networks are known to surpass human performance. This fact inspired us to apply the idea of transfer learning to understand the actual variability in clothing items. The principle of transfer learning consists in extracting the internal representa- tions formed in large convolutional networks pre-trained on general datasets, e.g., ImageNet, and visualizing its (similarity) structure. Together with transfer learn- ing, clustering algorithms and the image color schemes can be, namely, utilized when searching for related outfit items. Viable means applicable to generating new out- fits include deep belief networks and genetic algorithms enhanced by a convolutional network that models the outfit fitness. Although fashion-related recommendations remain highly subjective, the results we have achieved...
|
|
|
Increasing Reliability of Communication Networks
Hausner, Richard ; Komosný, Dan (referee) ; Koton, Jaroslav (advisor)
The bachelor's thesis deals with selected options for increasing reliability of communication networks. The basic protocols and network topologies are described in the thesis. In the second section the technologies of cascading, clustering and stacking network switches are discussed. The practical experiments and scenerios of connections, which are described in the aforementioned section, form a basis of their practical use proposal.
|
|
|
Artificial neural networks for macroeconomic data analysis
Padrón Peňa, Ildefonso ; Mrázová, Iveta (advisor) ; Kuboň, David (referee)
The analysis and prediction of macroeconomic time-series is a factor of great interest to national policymakers. However, economic analysis and forecast- ing are not simple tasks due to the lack of a precise model for the economy and the influence of external factors, such as weather changes or political decisions. Our research is focused on Spanish speaking countries. In this thesis, we study dif- ferent types of neural networks and their applicability for various analysis tasks, including GDP prediction as well as assessing major trends in the development of the countries. The studied models include multilayered neural networks, recur- sive neural networks, and Kohonen maps. Historical macroeconomic data across 17 Spanish speaking countries, together with France and Germany, over the time period of 1980-2015 is analyzed. This work then compares the performances of various algorithms for training neural networks, and demonstrates the revealed changes in the state of the countries' economies. Further, we provide possible reasons that explain the found trends in the data.
|
|
|
DRESS & GO: Deep belief networks and Rule Extraction Supported by Simple Genetic Optimization
Švaralová, Monika ; Mrázová, Iveta (advisor) ; Vomlelová, Marta (referee)
Recent developments in social media and web technologies offer new opportunities to access, analyze and process ever-increasing amounts of fashion-related data. In the appealing context of design and fashion, our main goal is to automatically suggest fashionable outfits based on the preferences extracted from real-world data provided either by individual users or gathered from the internet. In our case, the clothing items have the form of 2D-images. Especially for visual data processing tasks, recent models of deep neural networks are known to surpass human performance. This fact inspired us to apply the idea of transfer learning to understand the actual variability in clothing items. The principle of transfer learning consists in extracting the internal representa- tions formed in large convolutional networks pre-trained on general datasets, e.g., ImageNet, and visualizing its (similarity) structure. Together with transfer learn- ing, clustering algorithms and the image color schemes can be, namely, utilized when searching for related outfit items. Viable means applicable to generating new out- fits include deep belief networks and genetic algorithms enhanced by a convolutional network that models the outfit fitness. Although fashion-related recommendations remain highly subjective, the results we have achieved...
|
|
|
Artificial neural networks and their application in text analysis
Jankovič, Radovan ; Mrázová, Iveta (advisor) ; Neruda, Roman (referee)
This thesis is devoted to the area of sentiment analysis. Its goal is to discuss and compare various methods applicable to sentiment classification of short texts. When analyzing the described techniques, we will orient ourselves towards the context of social networks. Recently, this type of media became the source of vast amounts of data and the demand for its automatic processing is high. Interesting results have been obtained for clustering used in combination with supervised learning and convolution, which is primarily used for image data.
|
guest ::
