This thesis deals with convolutional neural networks. It is a kind of deep neural networks that are presently widely used mainly for image recognition and natural language processing. The thesis describes specifics of convolutional neural networks in comparison with traditional neural networks and is focused on inner computations in the process of learning. Convolutional neural networks typically consist of a different types of layers of neurons and the core part of this thesis is to demonstrate computations of individual types of layers. Learning demonstrating program of a simple convolutional network was designed and implemented using own implementation of neural network. Validity of the implementation was tested by training models for solving a classification task. Experiments with different types of architectures were conducted and their performance was compared.

Táto práca sa zaoberá využitím aproximovaných obvodov v neurónových sieťach so zámerom prínosu energetických úspor. K tejto téme už existujú štúdie, avšak väčšina z nich bola príliš špecifická k aplikácii alebo bola demonštrovaná v malom rozsahu. Pre dodatočné preskúmanie možností sme preto skrz netriviálne modifikácie open-source frameworku TensorFlow vytvorili platformu umožňujúcu simulovať používanie approximovaných obvodov na populárnych a robustných neurónových sieťach ako Inception alebo MobileNet. Bodom záujmu bolo nahradenie väčšiny výpočtovo náročných častí konvolučných neurónových sietí, ktorými sú konkrétne operácie násobenia v konvolučnách vrstvách. Experimentálne sme ukázali a porovnávali rozličné varianty a aj napriek tomu, že sme postupovali bez preučenia siete sa nám podarilo získať zaujímavé výsledky. Napríklad pri architektúre Inception v4 sme získali takmer 8% úspor, pričom nedošlo k žiadnemu poklesu presnosti. Táto úspora vie rozhodne nájsť uplatnenie v mobilných zariadeniach alebo pri veľkých neurónových sieťach s enormnými výpočtovými nárokmi.

The goal of this thesis is to design and create an automatic system for video anonymization. This system makes use of various object detectors on an image to ensure functionality, as well as active tracking of objects detected in this manner. Adjustments are later applied to these detected objects which ensure sufficient level of anonymization. The main asset of this system is speeding up the anonymization process of videos that can be published after.

Práca sa zaoberá spojeniami medzi štatistickou fyzikou a strojovým učením s dôrazom na základné princípy a ich dôsledky. Ďalej sa venuje obecným vlastnostiam spektroskopických dát a ich zohľadnení pri pokročilom spracovaní dát. Začiatok práce je venovaný odvodeniu partičnej sumy štatistického systému a štúdiu Isingovho modelu pomocou "mean field" prístupu. Následne, popri základnom úvode do strojového učenia, je ukázaná ekvivalencia medzi Isingovým modelom a Hopfieldovou sieťou - modelom strojového učenia. Na konci teoretickej časti je z Hopfieldovej siete odvodený model Restricted Boltzmann Machine (RBM). Vhodnosť použitia RBM na spracovanie spektroskopických dát je diskutovaná a preukázaná na znížení dimenzie týchto dát. Výsledky sú porovnané s bežne používanou Metódou Hlavných Komponent (PCA), spolu so zhodnotením prístupu a možnosťami ďalšieho zlepšovania.

Diplomova praca sa zameriava na oblast zaostrovania obrazkov tvari. V teoretickej casti prace budu prezentovane moderne metody zaostrovania obrazkov pomocou jedineho obrazku a metody editacie obrazkov. Prakticka cast sa zameria na pristupy rekonstrukcie obrazkov zo sekvencie poskodenych obrazkov. Viacere modely neuronovych sieti so vstupom pre viacero obrazkov budu zhotovene a vyhodnotene. Alternativny pristup v podobe balika nastrojov na editaciu obrazkov bude taktiez predstaveny. Tieto nastroje budu vyuzivat najmodernejsie pristupy k editacii obrazkov s cielom spojit vizualne prvky tvari zo vstupnej sekvencie obrazkov do jedneho finalneho vystupu. V zavere prace budu vsetky metody navzajom porovnane.

This diploma thesis is dedicated to one of the problems in wireless sensor networks – over the air upgrade (OTAU) of nodes. The requirements for upgrade and possible ways how to transfer new firmware image to nodes are stated in the first chapter. The second chapter is focused on solving the problem of firmware dissemination to whole network based on analysis of known protocols. The practical part of this thesis deals with OTAU design and implementation in Lightweight Mesh software stack from Atmel. Proposed system was tested on deRFnode platform with plugged in deRFmega128 module. The upgrade process of designed system is evaluated on test network in last part. Practical test results are compared with OTAU solution for BitCloud.

This master thesis deals with issue of trade on commodity market, especially the gold. It uses the artificial intelligence resources, more accurate non-linear auregressive neural network. The purpose is the prediction of the gold prices by indicators which has impact on the gold.

Diploma thesis is aimed to trainable image segmentation using deep neural networks. In the paper is explained the principle of digital image processing and image segmentation. In the paper is also explained the principle of artificial neural network, model of artificial neuron, training and activation of artificial neural network. In practical part of the paper is created an algorithm of sliding window to generate sub-images from image from magnetic rezonance. Generated sub-images are used to train, test and validate of the model of neural network. In practical part of the paper si created the model of the artificial neural network, which is used to trainable image segmentation. Model of the neural network is created using the Deeplearning4j library and it is optimized to parallel training using Spark library.

This diploma thesis examines the impact of the former US President Donald Trump's private Twitter account on agenda-building and how the Czech media work with information from this account. The diploma thesis is divided into two parts. The first part of the diploma thesis deals with the key theories and concepts of media studies such as the theory of agenda-setting, gatekeeping, news values, framing and intermedia agenda-setting. It also focuses on the contemporary form of political communication and the phenomenon of celebrity politics. The thesis also includes the overview of existing studies describing the political communication of the former US President Donald Trump on the social networking site Twitter and confirm the agenda-building role of this social network. The second part of the diploma thesis describes the research methodology and subsequent quantitative content analysis of news articles. The findings of quantitative content analysis are explained in the context of the theoretical concepts and previous studies. One of the main findings of this thesis is that Trump was able to some extent build media agenda, frame different topics and events and control his image in the media through his Twitter account.

This research project explores an area which had been touched only tangentially, being a comparative analysis of the idea and interpretations of friendship which emerge from the three vernacular collections attributed to the supervision of King Alfonso X of Castile (1252-1284): namely the Marian songs Cantigas de Santa María, the law code known as the Siete Partidas and the chronicle Estoria de España. These sources have been examined by adopting a thematic approach which has highlighted the existence of categories such as spiritual, religious and political friendships, as well as other forms of amicable relationships, including those between representatives of different religious, ethnic and social groups. Additionally, this study demonstrates that there was a conscious adoption of a specific lexicon of amicitia which contributed to reinforce either the opposition or the coincidence between friendship, companionship and counsellorship. Despite the undeniable inheritance of both classical eastern and western traditions, the works of the ‘Learned’ King present a peculiar idea of friendship which was deeply affected by contemporary historical contingencies and by the political and cultural projects of a sovereign who wanted to be regarded as a friend of his people, without denying, however, the unbridgeable gap which existed between different social groups. Interestingly, even if the Alfonsine works display a complicated range of relationships which envisage clear differences, they still outline a perfectly-balanced system within which the general and untouchable rules of friendship predominated, although in some cases certain variants were allowed in order to adapt such general requirements to contemporary social and political situations.